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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 33053
    Prev
    Next
    INDEX
    Explanations

    ingredients and recipes related to cooking, particularly focusing on chicken

    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
    +0.19
    0.9%
    62
    +0.09
    0.4%
    99
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.19
    0.09
    288
    +0.09
    0.17
    537
    +0.09
    0.10
    Negative Logits
    orsche
    -0.81
    INAL
    -0.74
    unci
    -0.74
    aylor
    -0.74
    ilities
    -0.69
    raints
    -0.69
    ilitarian
    -0.68
    itudinal
    -0.67
     Palestin
    -0.67
    ibel
    -0.66
    POSITIVE LOGITS
    pox
    1.08
     breasts
    0.89
     wings
    0.87
    bones
    0.85
     manure
    0.82
     thighs
    0.81
    hawk
    0.81
    meat
    0.80
    fish
    0.79
    bone
    0.77
    Activations Density 6.055%

    No Known Activations