© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 2206
    Prev
    Next
    INDEX
    Explanations

    HTML formatting tags

    oai_token-act-pair · gpt-3.5-turbo

    HTML elements or tags used in web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mathemat
    -0.80
     Chambers
    -0.79
     culinary
    -0.79
     migration
    -0.76
     councils
    -0.76
     Garry
    -0.75
     entrepreneurial
    -0.75
     sque
    -0.75
     experien
    -0.74
     CRA
    -0.73
    POSITIVE LOGITS
    amp
    1.77
    gt
    1.58
    lt
    1.42
    amps
    1.22
    album
    1.12
    md
    1.09
    attribute
    1.09
    AMP
    1.08
    ffff
    1.08
    src
    1.08
    Activations Density 0.013%

    No Known Activations