© 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. 3755
    Prev
    Next
    INDEX
    Explanations

    information related to technical procedures, guidelines, and processes

    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
    393
    +0.27
    1.0%
    372
    +0.14
    0.5%
    5
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.27
    0.08
    126
    +0.14
    0.07
    14
    +0.13
    0.06
    Negative Logits
    âĢİ
    -0.91
     Quote
    -0.79
     Rudd
    -0.75
    udeau
    -0.74
     Brief
    -0.74
    [
    -0.72
     rhet
    -0.71
    buster
    -0.70
     Removal
    -0.69
    lish
    -0.68
    POSITIVE LOGITS
    omething
    1.07
    inki
    1.06
     plenty
    1.00
     ample
    0.99
     sufficient
    0.94
     defin
    0.93
    nt
    0.92
     no
    0.92
    ogeneity
    0.91
    女
    0.90
    Activations Density 1.046%

    No Known Activations