© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 4602
    Prev
    Next
    INDEX
    Explanations

    locations or entities with the abbreviation "W" or "W**"

    oai_token-act-pair · gpt-3.5-turbo

    words containing the substring "W" and variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.82
    querque
    -0.74
     DEFENSE
    -0.71
    £ı
    -0.69
    vantage
    -0.66
    ãĥ¼ãĥĨ
    -0.65
    ij士
    -0.63
    ĪĴ
    -0.63
     Sapphire
    -0.62
    INAL
    -0.59
    POSITIVE LOGITS
    ipeg
    1.04
    nesday
    1.02
    ÅĤ
    0.98
    itzer
    0.84
    atche
    0.82
    bledon
    0.81
    hester
    0.81
    wright
    0.78
    lich
    0.76
    bucks
    0.76
    Activations Density 0.118%

    No Known Activations