© 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 EvalsExportsinterp-engineNEWAPI 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. 16325
    Prev
    Next
    INDEX
    Explanations

    references to American history and culture

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "American"

    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
    areth
    -0.77
     councillors
    -0.75
    âĶĢ
    -0.74
    reon
    -0.67
     sched
    -0.66
     councillor
    -0.65
    GG
    -0.64
    TL
    -0.63
    .>>
    -0.63
    =>
    -0.63
    POSITIVE LOGITS
     American
    3.40
    American
    2.98
     Americans
    2.48
    Americans
    2.37
     AMER
    2.32
     americ
    2.20
     America
    2.09
    America
    1.88
     Canadian
    1.77
     Australian
    1.69
    Activations Density 0.039%

    No Known Activations