© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5857
    Prev
    Next
    INDEX
    Explanations

    ways or methods to ensure or confirm something

    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
    162
    +0.17
    0.6%
    4
    +0.15
    0.5%
    748
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.17
    0.05
    75
    +0.15
    0.04
    8
    +0.14
    0.04
    Negative Logits
    EStreamFrame
    -1.08
    æ©
    -1.03
     ç¥ŀ
    -0.99
    bish
    -0.96
    PsyNetMessage
    -0.95
    gression
    -0.94
    çīĪ
    -0.91
     ILCS
    -0.89
    %]
    -0.89
    ahime
    -0.85
    POSITIVE LOGITS
    ially
    0.94
     valve
    0.85
    ariat
    0.84
     Lanka
    0.82
    imaru
    0.82
    awan
    0.81
    ties
    0.80
     adequate
    0.80
    jamin
    0.80
     customers
    0.80
    Activations Density 0.485%

    No Known Activations