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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 44934
    Prev
    Next
    INDEX
    Explanations

    positive descriptions or evaluations of something

    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
    304
    +0.13
    0.5%
    352
    +0.12
    0.5%
    718
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.13
    0.12
    228
    +0.12
    0.11
    718
    +0.12
    0.13
    Negative Logits
    isd
    -0.89
     Civilization
    -0.77
    ystem
    -0.76
    release
    -0.75
    ridor
    -0.75
    iHUD
    -0.73
    thur
    -0.72
    prus
    -0.72
    gow
    -0.70
    pai
    -0.69
    POSITIVE LOGITS
     anymore
    0.92
    agher
    0.88
     nor
    0.78
     enough
    0.74
    NJ
    0.71
     cruising
    0.70
     Carbuncle
    0.69
    iable
    0.69
     smelling
    0.68
     derby
    0.67
    Activations Density 9.438%

    No Known Activations