© 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. 576
    Prev
    Next
    INDEX
    Explanations

    numeric patterns and punctuation appearing in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    parentheses or other bracket-like symbols

    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
     Ups
    -0.70
     Tall
    -0.69
     tackling
    -0.68
     Puzz
    -0.67
     charge
    -0.67
     spir
    -0.67
     association
    -0.65
     Flor
    -0.65
     patriotic
    -0.64
     Sinai
    -0.64
    POSITIVE LOGITS
    iii
    1.38
    ii
    1.29
    1
    1.26
    a
    1.18
    *)
    1.17
    emphasis
    1.14
    II
    1.14
    i
    1.13
    ...)
    1.12
    âĢ¦)
    1.11
    Activations Density 0.054%

    No Known Activations