© 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. 8-RES-JB
    11. 7617
    Prev
    Next
    INDEX
    Explanations

    words that are followed by unusual characters, potentially indicating non-English language or special symbols

    oai_token-act-pair · gpt-3.5-turbo

    expressions of confusion or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ende
    -0.81
     increasingly
    -0.75
     brid
    -0.74
     shifting
    -0.73
     sculpt
    -0.73
     quir
    -0.73
     coral
    -0.72
     favour
    -0.72
     mutually
    -0.71
     raft
    -0.70
    POSITIVE LOGITS
    Advertisements
    1.38
    And
    1.28
    Copyright
    1.27
    Topics
    1.25
    Related
    1.22
    References
    1.22
    Behind
    1.21
    Anyone
    1.21
    Sources
    1.21
    Lots
    1.20
    Activations Density 0.592%

    No Known Activations