© 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. 6-RES-JB
    11. 23747
    Prev
    Next
    INDEX
    Explanations

    date and reference markers commonly used in written communication

    oai_token-act-pair · gpt-3.5-turbo

    elements of written communication, such as replies or messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istor
    -0.74
    onia
    -0.73
    AZ
    -0.69
    romeda
    -0.68
    angan
    -0.64
     sav
    -0.64
    ÄŁ
    -0.63
    ilan
    -0.63
    baby
    -0.63
    usters
    -0.63
    POSITIVE LOGITS
    ----------------------------------------------------------------
    0.87
     TABLE
    0.75
     ********************************
    0.68
    RFC
    0.67
    ////////////////////////////////
    0.66
    ================================================================
    0.64
     =================================================================
    0.63
     Caption
    0.63
    ================================
    0.62
     Sets
    0.61
    Activations Density 0.094%

    No Known Activations