© 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. 22643
    Prev
    Next
    INDEX
    Explanations

    code snippets containing specific instructions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to programming data types

    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
    hoe
    -0.76
    borough
    -0.75
    amaz
    -0.74
     Hutch
    -0.73
    ogens
    -0.73
    camp
    -0.73
    fires
    -0.72
    mob
    -0.71
    review
    -0.70
    abeth
    -0.69
    POSITIVE LOGITS
     integers
    1.67
     ASCII
    1.57
     integer
    1.50
     UTF
    1.49
     byte
    1.42
     Unicode
    1.40
     bytes
    1.39
     strings
    1.36
     decimal
    1.36
     numeric
    1.34
    Activations Density 0.332%

    No Known Activations