© 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. 4-RES-JB
    11. 13308
    Prev
    Next
    INDEX
    Explanations

    references to the name "Sat" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the term "Sat" and its variations

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

    No Comments

    Negative Logits
    enegger
    -0.82
    naire
    -0.79
    taining
    -0.72
    abwe
    -0.71
    ãģª
    -0.70
    OHN
    -0.69
    mental
    -0.68
    theless
    -0.68
     Annotations
    -0.67
    @#&
    -0.67
    POSITIVE LOGITS
    urn
    1.05
    chel
    0.94
    chell
    0.93
    yrs
    0.90
    chers
    0.86
    oshi
    0.84
    ilda
    0.84
    yr
    0.84
    rina
    0.84
    iva
    0.83
    Activations Density 0.006%

    No Known Activations