© 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. 11-RES-JB
    6. 3574
    Prev
    Next
    INDEX
    Explanations

    mentions of quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ullivan
    -0.67
    selves
    -0.66
    aldi
    -0.60
    mingham
    -0.60
    liction
    -0.59
    asts
    -0.59
     Borders
    -0.58
     cradle
    -0.58
    士
    -0.58
    ect
    -0.57
    POSITIVE LOGITS
     of
    1.04
    ngth
    0.90
     spent
    0.88
     thereof
    0.85
     expended
    0.85
     ingested
    0.80
     allotted
    0.80
     invested
    0.79
     owed
    0.76
     deducted
    0.76
    Activations Density 0.038%

    No Known Activations