© 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. 8-RES-JB
    11. 4587
    Prev
    Next
    INDEX
    Explanations

    names or titles of people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    brand names or specific identifiers related to media and culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.92
    anwhile
    -0.67
    espie
    -0.59
    代
    -0.58
    staking
    -0.57
    ierrez
    -0.57
    âĢ¢âĢ¢
    -0.55
    etheless
    -0.55
     dummy
    -0.52
    raints
    -0.52
    POSITIVE LOGITS
    Coin
    0.82
    coin
    0.75
    Game
    0.71
    Fest
    0.66
    Wiki
    0.66
    Forge
    0.66
    Hack
    0.65
    Star
    0.64
    Rap
    0.64
    Player
    0.64
    Activations Density 0.609%

    No Known Activations