© 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. 8395
    Prev
    Next
    INDEX
    Explanations

    references to computer mice and related technical information

    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
    578
    +0.19
    0.6%
    99
    +0.19
    0.6%
    583
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.19
    0.07
    99
    +0.19
    0.06
    288
    +0.15
    0.07
    Negative Logits
    ieves
    -1.15
    ivals
    -1.14
    ivism
    -1.09
    namese
    -1.06
    inyl
    -1.05
    rating
    -1.04
    orian
    -1.01
    lishes
    -1.00
    idential
    -1.00
    oday
    -1.00
    POSITIVE LOGITS
     cursor
    1.36
    pad
    1.20
     Mouse
    1.19
    lette
    1.19
     mice
    1.14
    cules
    1.10
     mouse
    1.09
     pointer
    1.06
    wheel
    1.02
     clicks
    0.98
    Activations Density 0.965%

    No Known Activations