© 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. 20292
    Prev
    Next
    INDEX
    Explanations

    government websites

    oai_token-act-pair · gpt-3.5-turbo

    references to government-related websites and resources

    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
     Aires
    -0.73
     Bucc
    -0.73
     Bale
    -0.63
     Crate
    -0.63
    Pie
    -0.63
     Toast
    -0.62
    ById
    -0.62
    cade
    -0.62
     Galile
    -0.62
     Isles
    -0.61
    POSITIVE LOGITS
    aukee
    0.83
    iets
    0.82
    uthor
    0.79
    ulnerability
    0.79
    gency
    0.78
    rition
    0.78
    gov
    0.76
    ugg
    0.76
    oppable
    0.76
    vernment
    0.73
    Activations Density 0.018%

    No Known Activations