© 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. 8082
    Prev
    Next
    INDEX
    Explanations

    comparative words related to improvement or progress

    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
    132
    +0.16
    0.6%
    389
    +0.16
    0.6%
    726
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.16
    0.10
    389
    +0.16
    0.08
    402
    +0.15
    0.07
    Negative Logits
    uca
    -0.95
    ãĥĥãĤ¯
    -0.94
    DragonMagazine
    -0.93
    utions
    -0.89
    pmwiki
    -0.87
     Reconstruction
    -0.87
    xtap
    -0.86
    liest
    -0.84
    imeter
    -0.84
    idated
    -0.84
    POSITIVE LOGITS
     importantly
    1.81
     than
    1.48
     refined
    1.15
     expensive
    1.11
     Than
    1.10
    ened
    1.09
     stringent
    1.06
     likely
    1.05
     sophisticated
    1.03
     efficient
    1.03
    Activations Density 1.473%

    No Known Activations