© 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. 3-RES-JB
    11. 13482
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    oai_token-act-pair · gpt-3.5-turbo

    instances of opening parentheses in code or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minded
    -0.83
    ylum
    -0.80
    amily
    -0.74
    earch
    -0.72
     entitle
    -0.72
    leep
    -0.71
    ĵĺ
    -0.71
     impeachment
    -0.69
    entimes
    -0.69
     seasonal
    -0.68
    POSITIVE LOGITS
    ...)
    1.03
    optional
    0.95
    partial
    0.93
    ())
    0.91
    default
    0.90
    ?)
    0.89
     ?)
    0.88
    emphasis
    0.88
    actual
    0.87
    sic
    0.87
    Activations Density 0.065%

    No Known Activations