© 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 Local
    9. 6-RES_SCL-AJT
    11. 31812
    Prev
    Next
    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    679
    +0.14
    0.6%
    213
    +0.12
    0.5%
    709
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.14
    0.06
    748
    +0.12
    0.03
    130
    +0.12
    0.02
    Negative Logits
    ufact
    -1.00
    fulness
    -0.86
    coni
    -0.77
     Lauder
    -0.74
    ocated
    -0.70
     Magicka
    -0.70
    grass
    -0.70
    fitting
    -0.69
     fullest
    -0.68
    itored
    -0.68
    POSITIVE LOGITS
    UE
    1.36
    uably
    1.09
    ues
    1.05
    WER
    0.99
    atar
    0.98
    ued
    0.95
    atari
    0.95
    ij士
    0.91
    uez
    0.90
    naire
    0.89
    Activations Density 6.019%

    No Known Activations