© 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. 1-RES-JB
    11. 20519
    Prev
    Next
    INDEX
    Explanations

    mentions of specific identities or people

    oai_token-act-pair · gpt-3.5-turbo

    references to various identities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    UTERS
    -0.71
    STRUCT
    -0.70
    GS
    -0.68
    ZE
    -0.65
    Stud
    -0.64
    odcast
    -0.64
    à¤
    -0.64
     Habit
    -0.62
    ×Ķ
    -0.62
    ש
    -0.62
    POSITIVE LOGITS
     identities
    1.36
    chwitz
    0.93
     identity
    0.93
    ativity
    0.91
    etter
    0.88
    afety
    0.86
    iosyncr
    0.85
    hips
    0.81
    ãĤ±
    0.80
    paces
    0.79
    Activations Density 0.009%

    No Known Activations