© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 9380
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms, specifically of "divorce"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Div" or related phrases, likely indicating topics around divorce or divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eston
    -0.73
     targ
    -0.71
     <@
    -0.71
    CVE
    -0.71
    uckle
    -0.67
    hooting
    -0.67
    uckland
    -0.67
    oak
    -0.66
     stimulus
    -0.66
    eware
    -0.66
    POSITIVE LOGITS
     Div
    4.02
    Div
    2.42
     Division
    1.71
    div
    1.51
     div
    1.39
     divisions
    1.38
     division
    1.26
    DIV
    1.24
    division
    1.21
     Divide
    1.19
    Activations Density 0.010%

    No Known Activations