© 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. 3-RES-JB
    11. 17272
    Prev
    Next
    INDEX
    Explanations

    expressions of preference or things that the speaker enjoys

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    phrases indicating personal preferences or likes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Americ
    -0.78
    ells
    -0.77
    inas
    -0.75
    bourne
    -0.71
    arta
    -0.71
    inoa
    -0.71
    hiba
    -0.70
    olin
    -0.70
    atar
    -0.70
    chin
    -0.69
    POSITIVE LOGITS
    lihood
    1.42
    liest
    0.96
    lier
    0.94
    minded
    0.89
     minded
    0.82
    liness
    0.82
     liking
    0.82
     ours
    0.78
    ably
    0.77
    76561
    0.77
    Activations Density 0.083%

    No Known Activations