© 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. 45737
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals

    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
    +0.17
    0.9%
    35
    +0.13
    0.7%
    167
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    688
    +0.17
    0.08
    326
    +0.13
    0.21
    167
    +0.13
    -0.03
    Negative Logits
    yip
    -0.65
    xual
    -0.65
    kees
    -0.64
    ndum
    -0.60
     hepatitis
    -0.59
    ccording
    -0.59
    76561
    -0.58
     waters
    -0.57
    igated
    -0.56
     srf
    -0.56
    POSITIVE LOGITS
    enson
    0.89
     Cheney
    0.86
    erson
    0.82
    inson
    0.81
    ible
    0.79
     Grayson
    0.76
    ERSON
    0.75
    ie
    0.73
    buster
    0.69
    ass
    0.69
    Activations Density 8.159%

    No Known Activations