© 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. 0-RES-JB
    11. 2430
    Prev
    Next
    INDEX
    Explanations

    the name "Seth" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals named Seth or Cain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aux
    -0.72
     wartime
    -0.71
     cane
    -0.70
     caravan
    -0.70
     par
    -0.69
    AU
    -0.69
     convertible
    -0.67
     postwar
    -0.67
     auxiliary
    -0.66
     gall
    -0.66
    POSITIVE LOGITS
     Seth
    3.76
     Cain
    1.37
     Noah
    1.27
     Jonah
    1.25
     Josh
    1.17
     Sasha
    1.16
     Ethan
    1.16
     Shawn
    1.15
     Adam
    1.14
     Trey
    1.14
    Activations Density 0.022%

    No Known Activations