© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 13612
    Prev
    Next
    INDEX
    Explanations

    keywords related to body parts, specifically limbs

    oai_token-act-pair · gpt-3.5-turbo

    references to limbs and body parts, particularly in medical or biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kered
    -0.78
     Forbidden
    -0.68
    Ö¼
    -0.66
    天
    -0.66
    GER
    -0.66
    ubb
    -0.66
    áµ
    -0.65
    keye
    -0.65
    dL
    -0.65
    girl
    -0.64
    POSITIVE LOGITS
     limbs
    1.17
    puter
    0.99
     nodd
    0.87
    nesota
    0.87
     limb
    0.86
     amput
    0.84
    ufact
    0.81
     ende
    0.78
    quartered
    0.76
    sembly
    0.76
    Activations Density 0.031%

    No Known Activations