© 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. 9-RES-JB
    11. 20871
    Prev
    Next
    INDEX
    Explanations

    words related to direct communication

    oai_token-act-pair · gpt-3.5-turbo

    sequences of repeated characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    vern
    -0.96
    chnology
    -0.88
    imore
    -0.82
    ciplinary
    -0.82
    ufact
    -0.79
    azo
    -0.79
    adra
    -0.78
    activation
    -0.76
    iking
    -0.76
    ignty
    -0.75
    POSITIVE LOGITS
     Ibid
    1.18
     Asked
    0.95
     Meanwhile
    0.93
     Provided
    0.91
     He
    0.90
     Eventually
    0.90
     Then
    0.88
     Additionally
    0.88
     Highlights
    0.87
     Added
    0.87
    Activations Density 0.104%

    No Known Activations