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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 34369
    Prev
    Next
    INDEX
    Explanations

    items or concepts related to research, medical studies, and psychological conditions

    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
    46
    +0.07
    0.5%
    711
    +0.07
    0.5%
    574
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.07
    0.29
    326
    +0.07
    0.26
    575
    +0.07
    0.19
    Negative Logits
    arian
    -0.59
    opus
    -0.59
    ea
    -0.53
    rique
    -0.51
    oin
    -0.50
    arians
    -0.50
    ing
    -0.50
    orious
    -0.50
    illes
    -0.50
    ugu
    -0.49
    POSITIVE LOGITS
    âĹ¼
    0.52
     minded
    0.49
    TRY
    0.46
    issy
    0.43
    STON
    0.43
    ãĤŃ
    0.42
    >>\
    0.42
    ï¸
    0.41
     misdem
    0.41
    verted
    0.41
    Activations Density 10.221%

    No Known Activations