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

    Neuronpedia

    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 Local
    9. 6-RES_SCL-AJT
    11. 39581
    Prev
    Next
    INDEX
    Explanations

    references to recipes and cooking instructions

    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
    447
    +0.13
    0.7%
    326
    +0.09
    0.5%
    288
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.13
    0.12
    189
    +0.09
    0.09
    326
    +0.09
    0.20
    Negative Logits
    ¥µ
    -0.71
    ITNESS
    -0.70
    ADRA
    -0.70
    afety
    -0.69
    razil
    -0.69
    ULTS
    -0.68
    WER
    -0.66
     Pension
    -0.66
    IBLE
    -0.65
    PsyNetMessage
    -0.64
    POSITIVE LOGITS
    ade
    0.87
     juice
    0.86
     bal
    0.75
     squee
    0.75
     peel
    0.74
     Lemon
    0.71
    picking
    0.70
    fruit
    0.69
    ous
    0.68
    ious
    0.67
    Activations Density 6.344%

    No Known Activations