© 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. 1398
    Prev
    Next
    INDEX
    Explanations

    references to news articles and journalism

    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
    489
    +0.14
    0.5%
    372
    +0.14
    0.5%
    296
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.14
    0.03
    238
    +0.14
    0.03
    296
    +0.14
    0.03
    Negative Logits
    cffffcc
    -1.28
     whistle
    -1.10
    EStreamFrame
    -1.05
     enthusi
    -1.03
    cffff
    -0.97
    iates
    -0.96
     phyl
    -0.95
     proport
    -0.95
    ascal
    -0.94
    existent
    -0.93
    POSITIVE LOGITS
     Shooting
    1.18
     Also
    1.06
     Sick
    1.04
     Gallery
    1.04
     Parties
    0.99
    chin
    0.98
    hen
    0.98
    chens
    0.97
     screenshots
    0.96
    KER
    0.96
    Activations Density 0.268%

    No Known Activations