© 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. 1035
    Prev
    Next
    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific female names

    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
    shit
    -0.79
    cffff
    -0.75
    asper
    -0.72
    ozy
    -0.71
    pelled
    -0.71
    pec
    -0.69
    yg
    -0.69
    doors
    -0.69
    sed
    -0.69
    */(
    -0.68
    POSITIVE LOGITS
     Louise
    1.12
     Marie
    1.08
     Thatcher
    1.06
     Anne
    1.06
     DeVos
    1.05
     Mae
    1.03
     Jane
    1.02
    Marie
    1.01
     herself
    1.00
     Margaret
    0.98
    Activations Density 0.064%

    No Known Activations