© 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. 6090
    Prev
    Next
    INDEX
    Explanations

    descriptions related to historical or significant events

    oai_token-act-pair · gpt-3.5-turbo

    notable historical or cultural landmarks

    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
     policies
    -0.73
     acad
    -0.72
     respectively
    -0.72
     lifestyles
    -0.72
    rosso
    -0.69
    doms
    -0.65
     markets
    -0.65
    querque
    -0.64
     estates
    -0.64
     selves
    -0.63
    POSITIVE LOGITS
     protr
    0.73
     symbol
    0.71
    shaped
    0.65
     piercing
    0.64
     diameter
    0.63
     retract
    0.63
     rotor
    0.62
     engraved
    0.61
     crochet
    0.61
     pierced
    0.61
    Activations Density 1.207%

    No Known Activations