© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 184
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical content

    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
    •Layer 6 UMAP region: e2e-recon outlier bottom right - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.33
    1.7%
    640
    +0.21
    1.1%
    160
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.33
    0.34
    160
    +0.21
    0.27
    442
    +0.13
    0.21
    Negative Logits
    enge
    -0.67
     gou
    -0.65
    enges
    -0.64
    krit
    -0.63
    borough
    -0.61
    thouse
    -0.59
     wip
    -0.59
     Kass
    -0.57
    entin
    -0.57
    enged
    -0.56
    POSITIVE LOGITS
    accompanied
    0.69
    division
    0.67
    SHARE
    0.64
    SEC
    0.64
    Commission
    0.63
    Commun
    0.62
    SCP
    0.62
    Const
    0.62
    sync
    0.62
    cult
    0.61
    Activations Density 3.433%

    No Known Activations