© 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. 10201
    Prev
    Next
    INDEX
    Explanations

    words related to medical substances and scientific terms

    oai_token-act-pair · gpt-3.5-turbo

    items that are categorized or listed

    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
    isine
    -0.82
    ocese
    -0.76
    ļéĨĴ
    -0.75
    ocide
    -0.73
    ongevity
    -0.71
    ocity
    -0.70
    oday
    -0.69
    ":"/
    -0.68
    \\\\\\\\
    -0.68
    west
    -0.65
    POSITIVE LOGITS
    those
    1.08
     aka
    1.07
     ones
    1.05
     cylinders
    0.97
     which
    0.94
     whereby
    0.94
     preferably
    0.92
     namely
    0.91
     hybrids
    0.90
     usually
    0.87
    Activations Density 0.263%

    No Known Activations