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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13284
    Prev
    Next
    INDEX
    Explanations

    mentions of notable or well-known figures, events, or concepts

    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
    +0.33
    1.6%
    288
    +0.12
    0.6%
    218
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.33
    0.14
    16
    +0.12
    0.08
    572
    +0.10
    0.09
    Negative Logits
    THER
    -0.78
    ilation
    -0.75
    ©¶æ
    -0.72
    heed
    -0.72
    iland
    -0.67
    ylon
    -0.64
    ajor
    -0.63
    idia
    -0.63
    otent
    -0.62
    required
    -0.61
    POSITIVE LOGITS
     landmarks
    0.82
     names
    0.73
     quotes
    0.73
    rities
    0.71
     quote
    0.70
     Circus
    0.69
    NESS
    0.66
     BaseType
    0.66
     surname
    0.65
     quotations
    0.64
    Activations Density 8.224%

    No Known Activations