© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21167
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific states or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific conditions or criteria

    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
    sonian
    -0.73
    endar
    -0.69
    enza
    -0.68
    ring
    -0.67
    enic
    -0.65
    LS
    -0.63
    ritz
    -0.63
    adesh
    -0.62
    cart
    -0.61
    ashington
    -0.61
    POSITIVE LOGITS
     conditions
    0.95
    ality
    0.95
     quo
    0.93
     deterior
    0.93
     condition
    0.88
     worsened
    0.87
     Conditions
    0.87
    aldehyde
    0.84
     permitting
    0.84
     deteriorated
    0.80
    Activations Density 0.045%

    No Known Activations