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. 20895
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a desire or request for information or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express desire or requests for information

    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
    livious
    -0.63
     wounding
    -0.63
     Olympia
    -0.57
     Reconstruction
    -0.57
     Tosh
    -0.55
     Reflect
    -0.54
     obser
    -0.54
     Emanuel
    -0.54
     injuring
    -0.54
    rup
    -0.54
    POSITIVE LOGITS
    reprene
    1.13
    only
    1.00
    zens
    0.83
    agh
    0.81
    on
    0.76
    gotten
    0.76
    zin
    0.75
    atile
    0.73
    anta
    0.72
    htar
    0.72
    Activations Density 0.044%

    No Known Activations