© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 23388
    Prev
    Next
    INDEX
    Explanations

    words related to names, potentially surnames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals associated with the suffix "ish."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rall
    -0.69
    oples
    -0.67
    wcs
    -0.66
     heartbeat
    -0.63
    heric
    -0.63
    brance
    -0.62
    STER
    -0.61
    orthern
    -0.61
    sites
    -0.60
     restrooms
    -0.59
    POSITIVE LOGITS
    nesses
    0.94
    liest
    0.93
    onest
    0.92
    chev
    0.86
    »Ĵ
    0.85
    washer
    0.85
    ings
    0.85
    tml
    0.84
    ness
    0.83
    ments
    0.83
    Activations Density 0.058%

    No Known Activations