© 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 EvalsExportsAPI 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. 6327
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or behaviors that involve pulling, attracting, influencing, or causing something to move in a specific direction

    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
    +0.22
    0.8%
    167
    +0.22
    0.7%
    26
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.22
    0.05
    26
    +0.22
    0.06
    167
    +0.17
    0.01
    Negative Logits
     bom
    -1.05
    nown
    -0.94
    ican
    -0.94
    icum
    -0.94
    onte
    -0.92
    terday
    -0.92
     gearing
    -0.88
    pher
    -0.84
    etheless
    -0.83
    unker
    -0.82
    POSITIVE LOGITS
    strings
    1.23
    card
    1.18
    cards
    1.17
     drawn
    1.13
     parallels
    1.13
    friend
    1.04
    minist
    1.01
     drawing
    1.01
    brid
    1.01
    draw
    1.00
    Activations Density 1.185%

    No Known Activations