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. 3-RES-JB
    6. 21647
    Prev
    Next
    INDEX
    Explanations

    actions related to body movements, like kneeling, crouching, and saluting

    oai_token-act-pair · gpt-3.5-turbo

    references to kneeling and posture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    allo
    -1.06
    izoph
    -0.82
    intosh
    -0.76
    oiler
    -0.73
    mis
    -0.71
    unn
    -0.70
    agent
    -0.69
    arro
    -0.69
    mal
    -0.69
    OTAL
    -0.69
    POSITIVE LOGITS
     kneeling
    1.05
     posture
    0.92
    ktop
    0.88
    lihood
    0.79
     nuns
    0.75
     kne
    0.75
     Pose
    0.73
     Committees
    0.71
     praying
    0.71
     vow
    0.70
    Activations Density 0.029%

    No Known Activations