© 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 EvalsExportsAPI 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. 6416
    Prev
    Next
    INDEX
    Explanations

    information related to the size of objects

    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
    153
    +0.16
    0.5%
    35
    +0.15
    0.5%
    653
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    653
    +0.16
    0.04
    255
    +0.15
    0.04
    638
    +0.15
    0.04
    Negative Logits
    perty
    -1.35
    veyard
    -1.28
    vous
    -1.19
    rea
    -1.18
    naissance
    -1.16
    iring
    -1.14
    idem
    -1.13
    issance
    -1.13
    oric
    -1.12
    endez
    -1.11
    POSITIVE LOGITS
     scale
    1.28
     stature
    1.16
     discrepancy
    1.15
     proportion
    1.11
     circumference
    1.10
     difference
    1.09
     intestine
    1.09
     scales
    1.07
     mismatch
    1.07
     allocation
    1.07
    Activations Density 0.723%

    No Known Activations