© 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. 9612
    Prev
    Next
    INDEX
    Explanations

    gender-specific terms, predominantly focusing on the differentiation between male and female

    oai_token-act-pair · gpt-3.5-turbo

    references to gender, particularly distinguishing between male and female

    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
    mun
    -0.73
    imony
    -0.64
     Grassley
    -0.63
    76561
    -0.62
     Jub
    -0.61
     Warn
    -0.60
    mat
    -0.60
    jen
    -0.59
    &
    -0.57
    itle
    -0.57
    POSITIVE LOGITS
     versa
    0.85
     alike
    0.84
     combatants
    0.82
     halves
    0.74
    senal
    0.72
     coasts
    0.70
    aiman
    0.68
     sides
    0.67
    peat
    0.66
     respectively
    0.66
    Activations Density 0.189%

    No Known Activations