© 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. 1-RES-JB
    11. 3301
    Prev
    Next
    INDEX
    Explanations

    mentions of the human body

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term 'body.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kafka
    -0.77
     Clover
    -0.66
     Nex
    -0.65
     Dickens
    -0.65
    BILITY
    -0.64
     Hoover
    -0.64
     Ans
    -0.64
     Monthly
    -0.62
     Liberty
    -0.61
     PBS
    -0.61
    POSITIVE LOGITS
    guards
    1.13
    anguage
    1.04
    builder
    0.99
    builders
    0.97
    body
    0.97
    fat
    0.92
    weight
    0.90
     body
    0.89
    guard
    0.89
    parts
    0.86
    Activations Density 0.021%

    No Known Activations