© 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 EvalsExportsAPI 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. 8-RES-JB
    11. 20394
    Prev
    Next
    INDEX
    Explanations

    spokespersons or representatives mentioned in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "spokesman" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spir
    -0.82
    iHUD
    -0.71
     [|
    -0.66
    bows
    -0.64
    dream
    -0.63
    VEN
    -0.63
     Reincarn
    -0.63
    shape
    -0.63
    Imp
    -0.62
    come
    -0.62
    POSITIVE LOGITS
     spokesman
    0.82
     Sean
    0.82
     Steph
    0.79
     emailed
    0.78
     Brendan
    0.77
     Brian
    0.75
    rored
    0.75
    ophe
    0.73
    atoon
    0.71
     Det
    0.70
    Activations Density 0.044%

    No Known Activations