© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 24132
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making and governance

    oai_token-act-pair · gpt-3.5-turbo

    content related to processes of agreement and consensus-building in discussions

    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
    ĸļ
    -0.65
    livious
    -0.63
    æ©
    -0.63
    umbn
    -0.62
    ãĥĥãĥī
    -0.62
     Moroc
    -0.61
     ÂŃ
    -0.58
    TW
    -0.58
     HuffPost
    -0.57
    SHARE
    -0.57
    POSITIVE LOGITS
     doesnt
    1.36
     shall
    1.29
     will
    1.28
     becomes
    1.25
     belongs
    1.17
     is
    1.17
     thereto
    1.15
     goes
    1.15
     depends
    1.14
     wont
    1.14
    Activations Density 0.924%

    No Known Activations