© 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. 11-RES-JB
    11. 24061
    Prev
    Next
    INDEX
    Explanations

    numerical values or ranges related to gaming attributes or abilities

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with game mechanics and statistics

    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
     Arpaio
    -0.69
    Reviewer
    -0.66
     Telegram
    -0.65
     lett
    -0.64
     watering
    -0.62
     Cinderella
    -0.62
    ressor
    -0.62
     Duterte
    -0.62
     Martha
    -0.61
    achelor
    -0.61
    POSITIVE LOGITS
    xp
    1.12
    gp
    1.08
    XP
    1.03
    HP
    1.00
    px
    0.99
    hp
    0.99
    %
    0.97
     mana
    0.96
    x
    0.93
     pts
    0.92
    Activations Density 0.055%

    No Known Activations