© 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. 5364
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or cities

    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
    326
    +0.16
    0.6%
    152
    +0.14
    0.5%
    238
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.12
    288
    +0.14
    0.15
    99
    +0.14
    0.08
    Negative Logits
    icle
    -0.99
    iary
    -0.98
    icles
    -0.97
    enegger
    -0.97
    owing
    -0.96
    eren
    -0.96
    onomy
    -0.94
    ULE
    -0.93
    æ³
    -0.93
    ãĥ¼ãĥ³
    -0.93
    POSITIVE LOGITS
     Pelicans
    1.22
     Parish
    1.17
     Saints
    1.02
     Purchase
    1.02
     Vie
    0.89
    gae
    0.89
     Revival
    0.88
     Soul
    0.87
    ModLoader
    0.82
     Rouge
    0.81
    Activations Density 2.286%

    No Known Activations