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

    Neuronpedia

    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 Local
    9. 6-RES_SCL-AJT
    11. 40689
    Prev
    Next
    INDEX
    Explanations

    not applicable

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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: Mostly-local line at bottom - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.29
    3.8%
    64
    +0.06
    0.8%
    351
    +0.05
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.29
    0.42
    64
    +0.06
    -0.34
    255
    +0.05
    0.17
    Negative Logits
    heid
    -0.19
    oshenko
    -0.19
     Deity
    -0.18
    ylan
    -0.18
     Canad
    -0.18
    bilt
    -0.18
    cedes
    -0.18
     offic
    -0.17
     office
    -0.17
     parap
    -0.17
    POSITIVE LOGITS
    âķIJ
    0.25
     Conclusion
    0.23
    ©¶æ
    0.21
    endix
    0.21
     Qiao
    0.20
    ________________________________
    0.20
     Finally
    0.20
    (*
    0.20
    ogether
    0.19
    results
    0.19
    Activations Density 23.286%

    No Known Activations