© 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. 6-RES-JB
    11. 5556
    Prev
    Next
    INDEX
    Explanations

    references to items of clothing, specifically pants

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "pantheon" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carbuncle
    -0.78
    SPONSORED
    -0.76
    KNOWN
    -0.72
     Jav
    -0.71
    ADE
    -0.71
    upon
    -0.71
    ITED
    -0.70
    ALD
    -0.68
     Sett
    -0.67
    é¾
    -0.66
    POSITIVE LOGITS
    heon
    1.63
     pant
    1.05
    ry
    1.03
    icip
    1.02
    agraph
    1.02
    hetically
    0.96
    agonist
    0.93
    neum
    0.91
    ancy
    0.91
    yrus
    0.89
    Activations Density 0.020%

    No Known Activations