© 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. 9-RES-JB
    11. 15910
    Prev
    Next
    INDEX
    Explanations

    terms related to the brain

    oai_token-act-pair · gpt-3.5-turbo

    references to the brain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Faust
    -0.65
     Bundy
    -0.65
    Dialog
    -0.64
     Bowie
    -0.64
     Arabia
    -0.64
    nesday
    -0.63
     Voters
    -0.63
    adoes
    -0.63
     Chamberlain
    -0.62
    riott
    -0.62
    POSITIVE LOGITS
    stem
    1.34
    washed
    1.32
    washing
    1.22
    wash
    1.14
    iac
    1.07
    waves
    1.03
    storms
    0.99
    fuck
    0.95
    dead
    0.91
    wave
    0.91
    Activations Density 0.034%

    No Known Activations