© 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. 10-RES-JB
    11. 6727
    Prev
    Next
    INDEX
    Explanations

    mentions of specific political groups and individuals

    oai_token-act-pair · gpt-3.5-turbo

    names and titles associated with organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Colossus
    -0.77
     Wilde
    -0.73
     Bott
    -0.71
     Doyle
    -0.71
     Nero
    -0.70
     Goose
    -0.69
    nard
    -0.68
     Bezos
    -0.67
     Olympus
    -0.67
    zzo
    -0.65
    POSITIVE LOGITS
    Islam
    1.30
     Islam
    1.12
     Sharia
    1.04
     mosque
    1.03
    Islamic
    1.00
     Islamic
    1.00
    iphate
    0.96
    iya
    0.96
    Muslim
    0.96
    Muslims
    0.95
    Activations Density 0.113%

    No Known Activations