© 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. 8443
    Prev
    Next
    INDEX
    Explanations

    the verb "do" in different variations and contexts

    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
    641
    +0.17
    0.6%
    78
    +0.16
    0.5%
    298
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.17
    0.10
    405
    +0.16
    0.10
    641
    +0.15
    0.10
    Negative Logits
    mares
    -1.08
    lights
    -1.07
    dayName
    -1.04
    hog
    -0.94
    ware
    -0.93
    Tai
    -0.92
    theless
    -0.90
    uru
    -0.90
    Reviewer
    -0.90
     Dise
    -0.89
    POSITIVE LOGITS
    omsday
    1.46
    pez
    1.23
    omething
    1.20
    ggy
    1.13
     something
    1.11
    oway
    1.10
    gging
    1.10
    le
    1.06
     anything
    1.06
    xx
    1.06
    Activations Density 1.404%

    No Known Activations