© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 1961
    Prev
    Next
    INDEX
    Explanations

    gender-specific mentions, with a focus on instances involving men

    oai_token-act-pair · gpt-3.5-turbo

    references to gender, specifically focusing on men

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Assembly
    -0.91
    ITS
    -0.81
    Closure
    -0.75
    UFF
    -0.73
    Clean
    -0.72
     Canaver
    -0.72
    Manufact
    -0.71
    IVERS
    -0.69
    Mount
    -0.68
    Ground
    -0.68
    POSITIVE LOGITS
    volent
    1.13
    folk
    0.91
    opausal
    0.91
     dominated
    0.74
     friendships
    0.74
     dominate
    0.73
     wiser
    0.73
    icide
    0.73
     hating
    0.73
     ejac
    0.72
    Activations Density 0.092%

    No Known Activations