© 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. 8-RES-JB
    11. 10835
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or entities

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and entities within the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    SPONSORED
    -0.60
    ttp
    -0.55
    Ô
    -0.54
    )",
    -0.53
    lihood
    -0.53
    !".
    -0.52
    tnc
    -0.52
    soType
    -0.50
    itored
    -0.50
    ;;
    -0.50
    POSITIVE LOGITS
     lacks
    1.01
     possesses
    0.89
     retains
    0.89
     lacked
    0.88
     suffers
    0.87
     underwent
    0.87
     tends
    0.86
     cannot
    0.85
     has
    0.85
     relies
    0.84
    Activations Density 0.623%

    No Known Activations