© 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. 8-RES-JB
    11. 21748
    Prev
    Next
    INDEX
    Explanations

    mentions of the Marvel character Thor

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character Thor

    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
    URES
    -0.73
    pring
    -0.69
    aminer
    -0.66
     sterling
    -0.66
    holders
    -0.66
    eq
    -0.65
    ecake
    -0.65
    es
    -0.65
    assetsadobe
    -0.62
    VICE
    -0.62
    POSITIVE LOGITS
    nton
    1.13
    sten
    1.12
     Ragnarok
    1.05
    chest
    0.92
    aldi
    0.89
    azine
    0.86
    bj
    0.83
    mand
    0.82
    agnar
    0.79
    ning
    0.79
    Activations Density 0.032%

    No Known Activations