© 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. 8243
    Prev
    Next
    INDEX
    Explanations

    text related to programming, software development, and technical instructions

    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
    640
    +0.19
    0.7%
    391
    +0.14
    0.5%
    389
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.19
    0.09
    640
    +0.14
    0.13
    679
    +0.13
    0.11
    Negative Logits
    etheless
    -1.23
    conservancy
    -1.09
    ascript
    -1.07
    onds
    -0.95
    ossession
    -0.91
    emaker
    -0.89
    gypt
    -0.89
    neys
    -0.87
    onding
    -0.85
    Ö¼
    -0.85
    POSITIVE LOGITS
     Okay
    1.04
     Bye
    1.03
     Aren
    1.01
     Introdu
    1.00
     Sounds
    0.99
     Well
    0.97
     Eh
    0.96
     Alright
    0.95
     Let
    0.94
     Subtle
    0.93
    Activations Density 2.420%

    No Known Activations