© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5417
    Prev
    Next
    INDEX
    Explanations

    knitting instructions related to specific stitches and techniques

    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
    578
    +0.14
    0.5%
    447
    +0.13
    0.5%
    633
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.04
    288
    +0.13
    0.04
    70
    +0.13
    0.03
    Negative Logits
    ysis
    -0.95
    inez
    -0.92
    gur
    -0.88
     Mub
    -0.78
     Bie
    -0.77
    oeuv
    -0.76
     Vie
    -0.74
    ouston
    -0.73
    utic
    -0.72
     Fres
    -0.72
    POSITIVE LOGITS
    CCC
    1.11
    ABLE
    0.82
    istani
    0.82
    ebook
    0.82
    stakes
    0.80
    tarians
    0.80
    verse
    0.80
     Sabha
    0.79
    magic
    0.78
     Digest
    0.78
    Activations Density 0.236%

    No Known Activations