© 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 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. 1380
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Seth."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Seth" in various contexts

    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
     vain
    -0.69
     sight
    -0.66
    patient
    -0.64
    breeding
    -0.64
    ogue
    -0.63
    arching
    -0.63
    cknow
    -0.63
    ffee
    -0.62
    judicial
    -0.62
    gain
    -0.61
    POSITIVE LOGITS
     Rollins
    0.95
    lings
    0.89
     Seth
    0.82
    Ö¼
    0.76
    nan
    0.73
    nikov
    0.73
     Guth
    0.72
     Heller
    0.71
    entially
    0.70
    tle
    0.70
    Activations Density 0.006%

    No Known Activations