© 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. 9-RES-JB
    11. 11324
    Prev
    Next
    INDEX
    Explanations

    instances where the word "dress" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of dress codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JV
    -0.74
    ntil
    -0.71
    venants
    -0.70
     Blessed
    -0.69
    founded
    -0.66
    SHIP
    -0.65
    stem
    -0.64
    ocalyptic
    -0.64
    irlf
    -0.62
    ignty
    -0.62
    POSITIVE LOGITS
     rehearsal
    1.12
    maker
    0.99
     gown
    0.94
     shirts
    0.89
     shoes
    0.87
     robes
    0.86
    pees
    0.84
     uniforms
    0.83
    makers
    0.83
     attire
    0.82
    Activations Density 0.030%

    No Known Activations