© 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. 16800
    Prev
    Next
    INDEX
    Explanations

    political affiliations and job titles

    oai_token-act-pair · gpt-3.5-turbo

    words related to political affiliations and demographics

    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
    lihood
    -0.81
    Downloadha
    -0.77
     Palest
    -0.66
    ++;
    -0.65
    escription
    -0.63
    amsung
    -0.63
    foundland
    -0.62
    yss
    -0.62
    redo
    -0.62
     Countries
    -0.61
    POSITIVE LOGITS
    itol
    0.79
    istrates
    0.74
    orate
    0.73
    quartered
    0.71
    ways
    0.67
    ivan
    0.67
    itent
    0.66
    rette
    0.63
     suburb
    0.62
    eways
    0.62
    Activations Density 0.318%

    No Known Activations