© 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. 0-RES-JB
    6. 20493
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Sale" occurring in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals involved in a significant event or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ign
    -0.67
     quint
    -0.67
     rect
    -0.66
    PN
    -0.66
     critical
    -0.64
     aud
    -0.63
     multic
    -0.62
     gymn
    -0.62
     primal
    -0.61
     wolf
    -0.61
    POSITIVE LOGITS
     Sale
    4.11
    sale
    1.73
     sale
    1.39
     Sell
    1.28
     Sales
    1.28
     Houth
    1.16
     Sold
    1.13
     Seller
    1.11
     Aden
    1.09
    Sales
    1.05
    Activations Density 0.015%

    No Known Activations