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. 10-RES-JB
    6. 15223
    Prev
    Next
    INDEX
    Explanations

    references to body parts and physical actions related to the head

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and related terms indicating ownership or relation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -1.05
     hereafter
    -0.74
    avis
    -0.74
    wik
    -0.73
    ãĥ´ãĤ¡
    -0.71
    liest
    -0.70
    soDeliveryDate
    -0.70
     Meadows
    -0.69
    Chall
    -0.69
    equality
    -0.68
    POSITIVE LOGITS
     fingers
    1.35
     fists
    1.35
     hips
    1.32
     own
    1.30
     gaze
    1.30
     knees
    1.28
     arms
    1.28
     toes
    1.23
     legs
    1.23
     lips
    1.21
    Activations Density 0.093%

    No Known Activations