© 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. 3656
    Prev
    Next
    INDEX
    Explanations

    references to specific themes or topics within a broader context

    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: Mixed in middle - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.22
    0.7%
    195
    +0.20
    0.7%
    459
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.08
    401
    +0.20
    0.06
    326
    +0.17
    0.06
    Negative Logits
    rets
    -1.05
    UGE
    -1.05
    aq
    -1.02
    dp
    -1.01
    lean
    -1.01
    pta
    -1.01
    rations
    -1.00
    OTOS
    -0.99
    lishes
    -0.99
    ÄŁ
    -0.98
    POSITIVE LOGITS
    ĸļ
    1.34
     theme
    1.33
     themes
    1.28
    theme
    1.22
     park
    1.10
     Theme
    1.06
    puter
    1.03
    ology
    1.03
    ography
    1.01
     Archdemon
    1.01
    Activations Density 0.899%

    No Known Activations