© 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. 19623
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific individual named Torres

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the last name "Torres" and specific characters or subjects

    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
    cause
    -0.87
    sg
    -0.82
    cv
    -0.79
    spring
    -0.76
    axter
    -0.76
    ously
    -0.74
    sylvania
    -0.73
    ride
    -0.72
    owed
    -0.72
    edition
    -0.72
    POSITIVE LOGITS
     Strait
    1.29
     Torres
    1.18
    heed
    0.82
    seys
    0.82
     Mata
    0.81
     Reyes
    0.72
    ters
    0.70
     Kul
    0.68
    mented
    0.67
    quin
    0.66
    Activations Density 0.017%

    No Known Activations