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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 304
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions for recipes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.14
    0.8%
    642
    +0.13
    0.7%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.08
    326
    +0.13
    0.07
    99
    +0.10
    0.04
    Negative Logits
    vernment
    -0.75
    SPONSORED
    -0.67
    Xi
    -0.56
    ³³³³³³³³
    -0.54
    bred
    -0.54
    OPLE
    -0.53
     Gutenberg
    -0.51
     Citizen
    -0.51
     debtor
    -0.51
    040
    -0.51
    POSITIVE LOGITS
    flies
    0.97
    cream
    0.95
    cup
    0.83
    isher
    0.73
    riter
    0.72
    worth
    0.71
    stroke
    0.69
    ishers
    0.68
    finger
    0.68
    fat
    0.67
    Activations Density 0.939%

    No Known Activations