© 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. 9303
    Prev
    Next
    INDEX
    Explanations

    speech attribution tags like "name:", "host:", and "byline:"

    oai_token-act-pair · gpt-3.5-turbo

    presence of transcript markers or speaker indications in a dialogue format

    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
    etheless
    -0.75
    lag
    -0.75
     rule
    -0.67
     dominate
    -0.65
     brewer
    -0.65
    alore
    -0.64
     ass
    -0.63
     ignor
    -0.63
    sole
    -0.63
     revolt
    -0.62
    POSITIVE LOGITS
     GOODMAN
    0.80
     Tonight
    0.77
    FACE
    0.76
    HAM
    0.75
     Yeah
    0.74
     VIDEO
    0.73
    ONSORED
    0.73
     Exactly
    0.71
     STORY
    0.71
     Cosponsors
    0.71
    Activations Density 0.041%

    No Known Activations