© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 20737
    Prev
    Next
    INDEX
    Explanations

    phrases indicating improbability or unlikeliness

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating isolation or lack of support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iple
    -0.79
    amba
    -0.71
    file
    -0.71
    alien
    -0.69
    ELD
    -0.69
    {"
    -0.68
    igr
    -0.67
    ided
    -0.67
    aim
    -0.66
    ells
    -0.66
    POSITIVE LOGITS
    acular
    0.82
     anything
    0.77
     necessarily
    0.72
     outright
    0.72
     anywhere
    0.70
     TAMADRA
    0.69
    lihood
    0.67
     endanger
    0.67
    anship
    0.66
     academia
    0.66
    Activations Density 0.063%

    No Known Activations