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. 5-RES-JB
    6. 6429
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and values, such as "param name" and "value"

    oai_token-act-pair · gpt-3.5-turbo

    structured data elements and parameters in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tasman
    -0.52
     Fresno
    -0.50
     Dru
    -0.49
    FML
    -0.48
    GD
    -0.47
     gent
    -0.46
     characterized
    -0.46
     bicy
    -0.45
     sorting
    -0.45
    conference
    -0.45
    POSITIVE LOGITS
     Wraith
    0.67
     msec
    0.60
    paren
    0.60
    utory
    0.59
    orean
    0.57
    )</
    0.56
     guiActive
    0.55
    strous
    0.54
    istani
    0.53
     rapes
    0.53
    Activations Density 0.899%

    No Known Activations