© 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 EvalsExportsinterp-engineNEWAPI 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. 9246
    Prev
    Next
    INDEX
    Explanations

    time intervals in a schedule

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly related to time or statistics

    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
    rament
    -0.81
    raltar
    -0.75
    azeera
    -0.75
    ilial
    -0.71
    ulet
    -0.71
    idates
    -0.70
    paio
    -0.69
     tremend
    -0.69
    necess
    -0.68
    achus
    -0.67
    POSITIVE LOGITS
    rm
    0.70
     [+]
    0.70
     footnote
    0.68
     WAR
    0.68
     WRITE
    0.67
    3333
    0.64
     [*]
    0.64
     TJ
    0.63
     =================================================================
    0.63
    jp
    0.63
    Activations Density 0.088%

    No Known Activations