© 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. 24177
    Prev
    Next
    INDEX
    Explanations

    questions or statements related to the truth or authenticity of a situation

    oai_token-act-pair · gpt-3.5-turbo

    statements questioning the truth or validity of a claim

    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
    ery
    -0.74
    oris
    -0.73
    ers
    -0.71
    igans
    -0.71
    players
    -0.67
    fold
    -0.67
    aters
    -0.66
    isms
    -0.66
    incent
    -0.65
    ller
    -0.63
    POSITIVE LOGITS
     termed
    0.57
     MPEG
    0.52
     Beetle
    0.52
    Eat
    0.52
     SATA
    0.50
     hamb
    0.50
     Centauri
    0.49
     trillions
    0.49
     psi
    0.49
    ulously
    0.49
    Activations Density 0.307%

    No Known Activations