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

    Neuronpedia

    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. 23779
    Prev
    Next
    INDEX
    Explanations

    the name "Uh" with different numerical values after it

    oai_token-act-pair · gpt-3.5-turbo

    repeated expressions or fillers in speech

    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
     Painter
    -0.81
    BOOK
    -0.79
    BALL
    -0.72
    uncture
    -0.66
    flies
    -0.64
    chnology
    -0.64
    ersen
    -0.61
     Roof
    -0.61
    ertodd
    -0.61
    OGR
    -0.60
    POSITIVE LOGITS
    ahah
    1.10
    awk
    0.98
    awks
    0.94
    hhhh
    0.91
    ansen
    0.87
    ospital
    0.83
    undai
    0.82
    azard
    0.81
    annah
    0.79
    vre
    0.79
    Activations Density 0.021%

    No Known Activations