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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 232
    Prev
    Next
    INDEX
    Explanations

    terms related to physical parts of the body, with a focus on legs

    oai_token-act-pair · gpt-3.5-turbo

    references to physical injury or body parts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.75
     Flavoring
    -0.69
    aukee
    -0.67
    eer
    -0.66
     Tycoon
    -0.64
     subp
    -0.64
    pload
    -0.62
     Nare
    -0.61
     Awoken
    -0.60
     groundwater
    -0.58
    POSITIVE LOGITS
    acies
    1.32
    puter
    1.04
    acy
    0.95
    spin
    0.89
     amput
    0.89
    chair
    0.88
    guards
    0.87
    oland
    0.86
    itimate
    0.86
    ajo
    0.85
    Activations Density 0.036%

    No Known Activations