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. 14576
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical ratios

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to percentages and voting statistics

    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
    sha
    -0.62
     novel
    -0.58
    ĨĴ
    -0.58
     periodic
    -0.57
     acknowled
    -0.57
     Caucasus
    -0.56
     histories
    -0.56
     flights
    -0.56
     bible
    -0.55
     subtitle
    -0.55
    POSITIVE LOGITS
    elsen
    0.74
    ideon
    0.73
    votes
    0.72
    percent
    0.72
    heimer
    0.71
    46
    0.70
    38
    0.70
    /-
    0.70
    49
    0.70
    Bernie
    0.69
    Activations Density 0.147%

    No Known Activations