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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22707
    Prev
    Next
    INDEX
    Explanations

    words related to clapping or similar actions

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases associated with "clumps" or "clumping."

    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
     Lank
    -0.58
     parties
    -0.57
     rece
    -0.57
    Madison
    -0.57
     unknown
    -0.55
    hyde
    -0.55
     Territory
    -0.54
     retri
    -0.54
     Madison
    -0.53
     Lans
    -0.53
    POSITIVE LOGITS
    ogged
    1.36
    ique
    1.21
    ashing
    1.18
    unky
    1.18
    umps
    1.18
    iche
    1.18
    amber
    1.16
    ojure
    1.16
    ums
    1.15
    amped
    1.14
    Activations Density 0.012%

    No Known Activations