© 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 EvalsExportsinterp-engineNEWAPI 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. 8002
    Prev
    Next
    INDEX
    Explanations

    numerical patterns, specifically related to pricing and schedules

    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
    183
    +0.21
    0.7%
    326
    +0.19
    0.6%
    216
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.21
    0.07
    693
    +0.19
    0.07
    507
    +0.15
    0.06
    Negative Logits
     tremend
    -1.34
    ileaks
    -1.23
    iciary
    -1.19
    icist
    -1.19
    ilater
    -1.18
    emort
    -1.18
     behavi
    -1.17
    ierrez
    -1.16
    ifully
    -1.15
    chwitz
    -1.14
    POSITIVE LOGITS
    91
    1.48
    34
    1.46
    92
    1.43
    87
    1.41
    94
    1.37
    71
    1.37
    50
    1.37
     Apostles
    1.36
    650
    1.36
    45
    1.34
    Activations Density 0.875%

    No Known Activations