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. 14561
    Prev
    Next
    INDEX
    Explanations

    percentages or numerical figures with a higher degree of change or growth

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to percentages and statistical changes

    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
     tools
    -0.62
     fame
    -0.61
     secrets
    -0.60
     instruments
    -0.60
     Rica
    -0.60
     adultery
    -0.59
     guts
    -0.59
     antagonists
    -0.59
     frameworks
    -0.58
     grounds
    -0.58
    POSITIVE LOGITS
    %-
    1.19
    -
    0.97
    fold
    0.88
    th
    0.88
    minute
    0.86
    %
    0.85
     percent
    0.82
    taboola
    0.81
    -,
    0.79
    percent
    0.79
    Activations Density 0.128%

    No Known Activations