© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2552
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "fur"

    oai_token-act-pair · gpt-3.5-turbo
    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
    ysis
    -0.87
     Howell
    -0.66
     Mald
    -0.64
     Rez
    -0.64
    orld
    -0.62
    ONES
    -0.61
     Arcade
    -0.61
     Exec
    -0.61
     Benz
    -0.59
     Somewhere
    -0.59
    POSITIVE LOGITS
    thur
    1.32
    rier
    1.18
    riers
    1.07
    fur
    1.04
    balls
    0.99
    isode
    0.94
    uit
    0.93
    rows
    0.92
    ried
    0.91
    ball
    0.90
    Activations Density 0.070%

    No Known Activations