© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10238
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "man" at varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "man" in various forms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ombo
    -0.67
    PsyNetMessage
    -0.65
    fuel
    -0.63
    ritical
    -0.62
    ignty
    -0.62
    heet
    -0.62
     fibre
    -0.62
    rolet
    -0.61
    avorite
    -0.60
    ifully
    -0.59
    POSITIVE LOGITS
    ifest
    1.40
    iac
    1.18
    ning
    1.09
    iasis
    1.08
    hattan
    1.06
    ufact
    1.04
    uscript
    0.99
    agements
    0.98
    aging
    0.97
    ned
    0.96
    Activations Density 0.069%

    No Known Activations