© 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. 17404
    Prev
    Next
    INDEX
    Explanations

    patterns of text that are likely structured as lists or bullet points

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of parentheses or similar symbols in the text

    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
     Tall
    -0.76
     Ups
    -0.73
     spir
    -0.68
     halfway
    -0.68
     Ros
    -0.67
     tackling
    -0.66
     Hung
    -0.63
     PowerShell
    -0.62
     Rising
    -0.61
     Rust
    -0.61
    POSITIVE LOGITS
    iii
    1.23
    ii
    1.21
    *)
    1.18
    ...)
    1.16
    1
    1.16
    emphasis
    1.15
    âĢ¦)
    1.14
    II
    1.09
    optional
    1.05
    iv
    1.05
    Activations Density 0.054%

    No Known Activations