© 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. 5275
    Prev
    Next
    INDEX
    Explanations

    phrases related to different key elements or parts making up a whole

    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
    487
    +0.10
    0.5%
    578
    +0.09
    0.4%
    399
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.10
    0.12
    189
    +0.09
    0.08
    288
    +0.09
    0.12
    Negative Logits
    Writ
    -0.69
    writ
    -0.68
    gha
    -0.65
    iannopoulos
    -0.63
    gee
    -0.63
    zee
    -0.63
    otos
    -0.63
    bill
    -0.63
    die
    -0.62
    Calling
    -0.62
    POSITIVE LOGITS
     crumble
    0.72
     requisite
    0.72
     nailed
    0.71
    etter
    0.69
     necessary
    0.69
     thereof
    0.67
     ingredients
    0.67
    omething
    0.65
     nails
    0.65
     melted
    0.64
    Activations Density 1.486%

    No Known Activations