© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3754
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing to newsletters or email updates

    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
    521
    +0.13
    0.5%
    500
    +0.13
    0.4%
    393
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.13
    0.10
    521
    +0.13
    0.03
    306
    +0.12
    0.06
    Negative Logits
    geist
    -1.05
    terday
    -0.97
    orld
    -0.96
     appell
    -0.96
    aceae
    -0.93
    wake
    -0.92
    imer
    -0.91
    uphem
    -0.90
    wagon
    -0.90
    onne
    -0.89
    POSITIVE LOGITS
     embed
    1.04
    iframe
    0.93
     promotional
    0.78
     respectful
    0.78
     unlocks
    0.78
    ordan
    0.78
     URL
    0.77
     copying
    0.76
     copyright
    0.75
     domain
    0.75
    Activations Density 1.876%

    No Known Activations