© 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. 0-RES-JB
    11. 1207
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical attributes, especially eyes and hair

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing physical attributes, particularly related to eyes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     value
    -0.68
     Stuart
    -0.66
     rec
    -0.64
     Reset
    -0.63
     trade
    -0.63
     recharge
    -0.63
     significantly
    -0.63
     reverse
    -0.63
     TP
    -0.62
     conf
    -0.62
    POSITIVE LOGITS
    eyed
    4.48
     eyed
    1.83
    haired
    1.80
    Ey
    1.76
    eyes
    1.72
    tailed
    1.56
    eye
    1.47
    faced
    1.46
    legged
    1.45
    headed
    1.37
    Activations Density 0.021%

    No Known Activations