© 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. 11-RES-JB
    11. 807
    Prev
    Next
    INDEX
    Explanations

    physical descriptions of people, particularly related to height, weight, and appearance

    oai_token-act-pair · gpt-3.5-turbo

    detailed physical descriptions of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SOS
    -0.69
     sacrific
    -0.62
    anca
    -0.62
    anwhile
    -0.62
    itors
    -0.62
    rily
    -0.61
    topia
    -0.57
     substitutes
    -0.57
     cease
    -0.56
    ettings
    -0.55
    POSITIVE LOGITS
    aucas
    1.13
     Caucasian
    1.11
    Hispanic
    1.00
     Hispanic
    0.96
     Caucas
    0.89
     complexion
    0.88
     gray
    0.86
     wearing
    0.86
     bald
    0.83
    arthy
    0.83
    Activations Density 0.200%

    No Known Activations