© 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. 3-RES-JB
    11. 1771
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Seth"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Seth"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    judicial
    -0.68
    sighted
    -0.67
     vain
    -0.67
     subp
    -0.66
     sight
    -0.66
    arching
    -0.65
    breeding
    -0.65
    ogue
    -0.64
    ffee
    -0.64
    secut
    -0.64
    POSITIVE LOGITS
     Rollins
    0.98
     Seth
    0.92
    lings
    0.86
    Ö¼
    0.75
     Rich
    0.72
     Guth
    0.72
    nikov
    0.70
    aceae
    0.70
     Heller
    0.70
     Rog
    0.68
    Activations Density 0.003%

    No Known Activations