Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 22570
    Prev
    Next
    INDEX
    Explanations

    mentions of public figures and their roles or affiliations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their roles or professions

    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
    Âł
    -0.70
    SPONSORED
    -0.69
    ".[
    -0.69
    Firstly
    -0.68
     whilst
    -0.68
    Contents
    -0.66
    !".
    -0.64
    ãĥİ
    -0.64
     [â̦]
    -0.62
     ().
    -0.61
    POSITIVE LOGITS
     spokeswoman
    0.94
     echoed
    0.90
     spokesman
    0.89
     countered
    0.88
     disagreed
    0.82
     disagrees
    0.77
     criticized
    0.76
     applauded
    0.73
     meanwhile
    0.73
     objected
    0.70
    Activations Density 0.899%

    No Known Activations