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. 4268
    Prev
    Next
    INDEX
    Explanations

    information related to technical specifications and assembly instructions, especially regarding mechanical components

    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
    +0.16
    0.9%
    679
    +0.10
    0.5%
    678
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.16
    0.26
    288
    +0.10
    0.30
    258
    +0.09
    0.21
    Negative Logits
    à¨
    -0.58
    à©
    -0.56
     experien
    -0.55
    Õ
    -0.53
    âĸ¬
    -0.53
    ABLE
    -0.51
    BUG
    -0.51
    ×IJ
    -0.51
    ×ŀ
    -0.50
    à¤
    -0.49
    POSITIVE LOGITS
    hips
    1.17
    hip
    1.01
    paces
    1.01
    uggest
    0.90
    hops
    0.89
    poons
    0.87
    heet
    0.87
    etter
    0.85
    chool
    0.85
    uits
    0.83
    Activations Density 14.332%

    No Known Activations