© 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. 4-RES-JB
    11. 6184
    Prev
    Next
    INDEX
    Explanations

    names of countries, especially Serbia

    oai_token-act-pair · gpt-3.5-turbo

    references to the country Serbia and its historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITNESS
    -0.86
     largeDownload
    -0.83
    owler
    -0.73
    ership
    -0.72
    enegger
    -0.69
    intosh
    -0.69
    iances
    -0.68
    tions
    -0.67
    ersen
    -0.67
    ened
    -0.67
    POSITIVE LOGITS
    pling
    0.85
    plings
    0.81
    vier
    0.75
    uous
    0.75
    addle
    0.73
    chn
    0.71
    clair
    0.71
    chnology
    0.70
    wcsstore
    0.67
    ifle
    0.67
    Activations Density 0.022%

    No Known Activations