© 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. 4-RES-JB
    11. 15627
    Prev
    Next
    INDEX
    Explanations

    mentions of gender-specific words, particularly focusing on comparisons between men and women

    oai_token-act-pair · gpt-3.5-turbo

    references to men and their roles in society

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

    No Comments

    Negative Logits
    Assembly
    -0.78
    rawdownloadcloneembedreportprint
    -0.77
    UFF
    -0.75
    ITS
    -0.74
    REDACTED
    -0.74
    Fab
    -0.71
    Sym
    -0.69
    Ward
    -0.69
    REC
    -0.68
    COMPLE
    -0.67
    POSITIVE LOGITS
    volent
    1.08
    opausal
    1.00
    folk
    0.98
     genitals
    0.85
    ager
    0.85
    icide
    0.81
    isers
    0.77
    hood
    0.76
     ejac
    0.73
    cius
    0.72
    Activations Density 0.113%

    No Known Activations