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

    Neuronpedia

    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. 8-RES-JB
    11. 17793
    Prev
    Next
    INDEX
    Explanations

    individuals or entities who support or are fans of specific things, such as sports teams or public figures

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fandom and support for various entities or individuals

    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
    olars
    -0.70
    itudes
    -0.69
    ambers
    -0.63
    ammers
    -0.63
    erity
    -0.62
    brids
    -0.62
    liam
    -0.62
    onies
    -0.61
    eworks
    -0.61
     Whites
    -0.60
    POSITIVE LOGITS
    lier
    0.89
     of
    0.87
     thereof
    0.79
    Reviewer
    0.74
     reminder
    0.70
     inhibitor
    0.70
    ollower
    0.69
     fixture
    0.69
    atical
    0.68
    hetical
    0.68
    Activations Density 0.141%

    No Known Activations