Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40222
    Prev
    Next
    INDEX
    Explanations

    references to arts-related topics such as art, culture, crafts, and artistic expressions

    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
    +0.18
    0.9%
    288
    +0.17
    0.8%
    679
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.25
    124
    +0.17
    0.13
    561
    +0.15
    0.10
    Negative Logits
    odder
    -0.71
    aded
    -0.71
     Adin
    -0.70
     Paragu
    -0.68
    ading
    -0.68
    utations
    -0.68
    utable
    -0.65
    agher
    -0.65
    utation
    -0.64
    ishable
    -0.62
    POSITIVE LOGITS
    manship
    1.14
    esian
    1.04
    cape
    0.97
    pace
    0.84
     arts
    0.83
    chool
    0.81
    alon
    0.78
    isans
    0.77
    smanship
    0.75
     Profession
    0.75
    Activations Density 10.347%

    No Known Activations