© 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. 6439
    Prev
    Next
    INDEX
    Explanations

    words related to individuals or things named "Cand" or variations of that name

    oai_token-act-pair · gpt-3.5-turbo

    references to 'candle' or related terms

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
    FactoryReloaded
    -0.73
    HF
    -0.68
     pity
    -0.65
    FG
    -0.61
    GV
    -0.61
     centrif
    -0.61
     disparate
    -0.60
    ãĤ´ãĥ³
    -0.60
     phased
    -0.60
    POSITIVE LOGITS
    idates
    1.48
    lest
    1.30
    idate
    1.25
    les
    0.98
    ulum
    0.95
    illo
    0.93
    raper
    0.92
    reon
    0.91
    escent
    0.90
    encies
    0.89
    Activations Density 0.022%

    No Known Activations