© 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. 10-RES-JB
    11. 10786
    Prev
    Next
    INDEX
    Explanations

    exclamations and announcements in text

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory statements or emphatic expressions

    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
     mistrust
    -0.89
     dehuman
    -0.84
     distrust
    -0.84
     outwe
    -0.80
     contrasted
    -0.80
     discour
    -0.80
     outweigh
    -0.79
     bias
    -0.78
     contrasts
    -0.78
     oneself
    -0.78
    POSITIVE LOGITS
    Atl
    1.27
    Yesterday
    1.25
    Sony
    1.23
    Congratulations
    1.20
    TOR
    1.18
    Following
    1.14
    Rum
    1.13
    UPDATE
    1.13
    Today
    1.11
    Starting
    1.09
    Activations Density 0.373%

    No Known Activations