© 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. 3-RES-JB
    11. 16969
    Prev
    Next
    INDEX
    Explanations

    words related to nobility or ranking

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or characters associated with "Count."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.74
    BIT
    -0.72
    utics
    -0.67
    ा
    -0.65
    uberty
    -0.64
    qqa
    -0.63
     tram
    -0.62
    utic
    -0.62
    wx
    -0.62
    obyl
    -0.62
    POSITIVE LOGITS
    enance
    1.50
    ess
    1.15
    esses
    1.10
    ries
    1.09
    downs
    0.85
    ette
    0.84
    ies
    0.83
    s
    0.81
    parts
    0.77
    ing
    0.77
    Activations Density 0.006%

    No Known Activations