© 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. 3724
    Prev
    Next
    INDEX
    Explanations

    Situations or events that involve legal violations or controversial actions, often described in detail

    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
    +0.27
    1.1%
    138
    +0.21
    0.9%
    213
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.27
    -0.01
    640
    +0.21
    0.45
    266
    +0.16
    0.42
    Negative Logits
     destro
    -0.78
     eleph
    -0.76
    ppe
    -0.75
     rig
    -0.73
    aign
    -0.72
     abandon
    -0.72
    cture
    -0.70
    aundering
    -0.70
    pload
    -0.67
    aced
    -0.67
    POSITIVE LOGITS
    advertisement
    0.92
    Overview
    0.92
    Preview
    0.91
    Abstract
    0.90
    WASHINGTON
    0.87
    SAN
    0.87
    Community
    0.86
    Contents
    0.86
    SHARE
    0.85
    Reviewed
    0.84
    Activations Density 27.254%

    No Known Activations