© 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. 10575
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to scientific experiments and data collection

    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
    288
    +0.16
    0.7%
    294
    +0.14
    0.6%
    701
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.08
    701
    +0.14
    0.06
    326
    +0.13
    0.07
    Negative Logits
     priced
    -0.81
    vati
    -0.81
    ccording
    -0.78
    ched
    -0.78
     stake
    -0.77
    66666666
    -0.74
    ============
    -0.73
    que
    -0.70
    BOOK
    -0.69
    ching
    -0.68
    POSITIVE LOGITS
    aceutical
    1.07
    obile
    1.02
    ont
    0.98
    asonic
    0.94
    obiles
    0.94
    ichael
    0.91
    aintain
    0.90
    andom
    0.89
    otor
    0.88
    agnetic
    0.87
    Activations Density 0.833%

    No Known Activations