© 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. 17180
    Prev
    Next
    INDEX
    Explanations

    specific patterns of capitalized words within a document, potentially related to specific names or titles

    oai_token-act-pair · gpt-3.5-turbo

    references to ownership or possession

    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
     to
    -0.82
    to
    -0.64
     unto
    -0.62
     toward
    -0.59
     TO
    -0.57
     ta
    -0.54
    To
    -0.52
     To
    -0.50
     towards
    -0.49
     thereto
    -0.48
    POSITIVE LOGITS
    ailability
    0.64
    etsk
    0.56
    İĭ
    0.54
    æł
    0.50
    ilage
    0.50
    çİĭ
    0.49
    天
    0.48
    uably
    0.48
    士
    0.48
    iframe
    0.48
    Activations Density 1.072%

    No Known Activations