© 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. 6471
    Prev
    Next
    INDEX
    Explanations

    strings enclosed in brackets ']' with a high degree of activation

    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
    132
    +0.21
    0.6%
    160
    +0.17
    0.5%
    302
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.21
    0.06
    6
    +0.17
    0.06
    593
    +0.17
    0.05
    Negative Logits
    Ń·
    -1.56
    İĭ
    -1.48
    ©¶æ¥µ
    -1.46
    ĪĴ
    -1.28
    ĻĤ
    -1.27
    Ļ½
    -1.25
    hement
    -1.20
    ĸļ
    -1.19
    ij士
    -1.16
    ±
    -1.16
    POSITIVE LOGITS
    +)
    1.09
    report
    1.01
    Management
    0.99
     Manifest
    0.99
     =>
    0.98
     onwards
    0.97
    REDACTED
    0.97
     Flavoring
    0.96
    UAL
    0.96
    },"
    0.95
    Activations Density 0.745%

    No Known Activations