© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 4838
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Gambling"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific gaming community 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
     floral
    -0.74
     ÂŃ
    -0.74
     balloon
    -0.73
     bou
    -0.71
     marg
    -0.70
     aux
    -0.69
     piping
    -0.67
     poems
    -0.66
     undo
    -0.66
     ¶
    -0.66
    POSITIVE LOGITS
     Gam
    2.37
     Gaming
    2.26
    Gam
    2.20
    Gamer
    2.11
    Gaming
    2.10
     Gamer
    2.05
    gamer
    1.97
     gamer
    1.76
     Esports
    1.75
     eSports
    1.71
    Activations Density 0.039%

    No Known Activations