© 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. 10856
    Prev
    Next
    INDEX
    Explanations

    words related to the specific word "risk"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'isk', which seems to be a recurring theme in the content

    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
    stration
    -0.82
    frey
    -0.81
    naissance
    -0.76
    cemic
    -0.73
    ricks
    -0.69
    nt
    -0.68
    ICAN
    -0.65
    TERN
    -0.65
    bugs
    -0.65
    brates
    -0.64
    POSITIVE LOGITS
    atchewan
    0.87
    patrick
    0.80
    ernel
    0.77
    imon
    0.74
    ozy
    0.74
    irts
    0.74
    onduct
    0.72
    mallow
    0.70
    oot
    0.69
    ansas
    0.68
    Activations Density 0.042%

    No Known Activations