© 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 EvalsExportsinterp-engineNEWAPI 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. 9167
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word 'men'

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "men."

    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
    IVERS
    -0.84
    REDACTED
    -0.76
    Deal
    -0.75
    Accessory
    -0.72
    REC
    -0.71
    VICE
    -0.70
    EV
    -0.69
    KEN
    -0.69
    Main
    -0.68
    Democratic
    -0.67
    POSITIVE LOGITS
    volent
    1.30
    opausal
    1.26
    endez
    1.20
    ager
    1.13
    uscript
    1.05
    aced
    1.01
    orah
    1.00
    aces
    0.93
    agers
    0.91
    folk
    0.91
    Activations Density 0.051%

    No Known Activations