© 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. 15181
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, specifically with the substring "ans" frequently appearing in the activations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Fr" or variations thereof related to locations, specifically San Francisco

    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
     Jinn
    -0.80
    izu
    -0.68
     Izan
    -0.66
     Contrast
    -0.64
     Siren
    -0.64
     Archdemon
    -0.63
    Redd
    -0.63
    atsu
    -0.62
     Lith
    -0.61
     Khe
    -0.61
    POSITIVE LOGITS
    isco
    0.98
    ruary
    0.79
    ulent
    0.78
    atism
    0.76
    rance
    0.74
    nce
    0.70
    furt
    0.69
    fur
    0.67
    acies
    0.67
    ateurs
    0.65
    Activations Density 0.083%

    No Known Activations