© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7420
    Prev
    Next
    INDEX
    Explanations

    comparative terms or phrases indicating a higher degree or quantity of something, particularly in relation to data or statistics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.17
    0.8%
    647
    +0.14
    0.7%
    726
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.17
    0.10
    647
    +0.14
    0.09
    389
    +0.11
    0.08
    Negative Logits
    xtap
    -0.82
    æ©
    -0.76
    DragonMagazine
    -0.75
    comings
    -0.74
     NCT
    -0.73
    heid
    -0.72
    utions
    -0.72
    etimes
    -0.70
    ipment
    -0.68
    atan
    -0.68
    POSITIVE LOGITS
     than
    1.26
     efficient
    1.13
     complicated
    1.11
     accurate
    1.04
     important
    1.02
     expensive
    1.01
     likely
    1.00
     stringent
    1.00
     inclined
    0.99
     manageable
    0.99
    Activations Density 0.740%

    No Known Activations