© 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. 998
    Prev
    Next
    INDEX
    Explanations

    data related to research studies

    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
    389
    +0.15
    0.5%
    455
    +0.14
    0.5%
    253
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.15
    0.06
    190
    +0.14
    0.06
    455
    +0.13
    0.06
    Negative Logits
    halla
    -0.94
    oÄŁ
    -0.91
    omnia
    -0.89
     Brav
    -0.86
    âĹ¼
    -0.85
    Draft
    -0.84
     Origins
    -0.84
    DK
    -0.84
     Advis
    -0.83
     Events
    -0.82
    POSITIVE LOGITS
     than
    1.70
    ened
    1.37
    ening
    1.17
     forgiving
    1.17
     stringent
    1.07
    than
    1.03
     conspicuous
    1.01
     manageable
    1.01
     fortunate
    1.00
     Than
    1.00
    Activations Density 0.918%

    No Known Activations