© 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. 6-RES-JB
    11. 12791
    Prev
    Next
    INDEX
    Explanations

    references to males or men

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the term "man" in various contexts

    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
    PsyNetMessage
    -0.83
    IVERS
    -0.76
    inventoryQuantity
    -0.72
    IFT
    -0.69
    Import
    -0.69
    Regular
    -0.68
    Democratic
    -0.68
    ICE
    -0.67
    ython
    -0.67
    Analysis
    -0.66
    POSITIVE LOGITS
    hunt
    1.23
    gling
    1.20
    nered
    1.16
    hood
    1.11
    uscript
    1.10
    osphere
    1.03
    hattan
    1.02
    volent
    0.97
    ifest
    0.95
    ger
    0.94
    Activations Density 0.063%

    No Known Activations