© 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. 11-RES-JB
    11. 11544
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "by" followed by a positive trait or action describing the subject

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "By" followed by a number, indicating sources or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.86
    umble
    -0.70
    icken
    -0.69
    BAT
    -0.67
    ptions
    -0.67
    MpServer
    -0.65
    hetics
    -0.65
    FUL
    -0.64
    ickets
    -0.64
    PLA
    -0.61
    POSITIVE LOGITS
     contrast
    1.39
     comparison
    1.10
    stand
    1.04
     definition
    1.02
     implication
    1.00
     analogy
    1.00
     coincidence
    0.98
     virtue
    0.97
    pass
    0.93
    catch
    0.91
    Activations Density 0.038%

    No Known Activations