Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10855
    Prev
    Next
    INDEX
    Explanations

    references to body parts, particularly legs, thighs, feet, hands, and wings

    oai_token-act-pair · gpt-3.5-turbo

    references to body parts and physical features

    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
     claimant
    -0.66
    eers
    -0.64
    naire
    -0.59
     referen
    -0.58
     insider
    -0.58
     antidepressant
    -0.58
     retrospective
    -0.57
     psychiatry
    -0.56
     sender
    -0.56
     atheist
    -0.56
    POSITIVE LOGITS
    pring
    1.28
    mith
    1.25
    uits
    1.24
    peed
    1.23
    poons
    1.21
    pots
    1.19
    cape
    1.18
    creen
    1.18
    pread
    1.17
    ight
    1.12
    Activations Density 0.195%

    No Known Activations