© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 1789
    Prev
    Next
    INDEX
    Explanations

    SELECT statements or keywords often used in computer programming and database querying

    oai_token-act-pair · gpt-3.5-turbo

    references to "select" or selection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nerv
    -0.72
    FORE
    -0.71
    STD
    -0.70
    loo
    -0.68
    ipple
    -0.66
    ijk
    -0.66
    abwe
    -0.65
    peria
    -0.64
    chief
    -0.64
    nz
    -0.62
    POSITIVE LOGITS
    ivity
    1.26
    ively
    1.08
    ives
    0.97
    ivities
    0.86
    prising
    0.84
    cuts
    0.83
    inations
    0.80
    ions
    0.77
    orate
    0.76
    ive
    0.74
    Activations Density 0.028%

    No Known Activations