© 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. 36283
    Prev
    Next
    INDEX
    Explanations

    predictions or possibilities

    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
    566
    +0.10
    0.5%
    447
    +0.10
    0.5%
    462
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.10
    0.20
    718
    +0.10
    0.20
    49
    +0.09
    0.17
    Negative Logits
    LD
    -0.56
    raper
    -0.54
     Basics
    -0.53
     Delicious
    -0.53
    updated
    -0.52
     TED
    -0.52
     Ment
    -0.51
     Composite
    -0.51
     Fine
    -0.51
    retty
    -0.51
    POSITIVE LOGITS
     be
    0.83
     perceive
    0.78
     feas
    0.78
     consume
    0.77
     inevitably
    0.76
    »Ĵ
    0.75
     deem
    0.73
     receive
    0.70
     achieve
    0.70
     introduce
    0.69
    Activations Density 11.066%

    No Known Activations