Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 21942
    Prev
    Next
    INDEX
    Explanations

    words related to strong interest or preoccupation with a particular topic

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong fixation or preoccupation with certain subjects or ideas

    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
    stood
    -0.81
    \\\\\\\\
    -0.76
    soType
    -0.73
    DragonMagazine
    -0.69
    OUT
    -0.69
    received
    -0.63
    Medic
    -0.61
    Reviewed
    -0.61
    gs
    -0.61
    GG
    -0.61
    POSITIVE LOGITS
    ishly
    0.85
    iously
    0.84
     fascination
    0.79
    ilyn
    0.73
     fascinated
    0.73
    ischer
    0.71
    olescent
    0.71
    minist
    0.71
    ively
    0.70
     hobby
    0.69
    Activations Density 0.042%

    No Known Activations