© 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. 10002
    Prev
    Next
    INDEX
    Explanations

    technical or industry-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to controversial topics or debates

    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
    ISSION
    -0.71
    urden
    -0.67
    mission
    -0.65
    itiveness
    -0.63
    oyer
    -0.63
    0000000
    -0.62
    "}],"
    -0.62
    =""
    -0.61
    =\"
    -0.61
    ]]
    -0.61
    POSITIVE LOGITS
     notably
    1.17
     notable
    1.10
     examples
    1.10
     occasional
    1.01
     recently
    1.00
     recent
    0.97
     scandals
    0.96
    recent
    0.95
     famously
    0.95
     exceptions
    0.93
    Activations Density 0.725%

    No Known Activations