© 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. 8-RES-JB
    11. 19266
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ford"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ford" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Magikarp
    -0.94
    ntil
    -0.92
    undo
    -0.80
    PDATE
    -0.75
    ngth
    -0.73
    PER
    -0.71
    GoldMagikarp
    -0.70
    vana
    -0.69
    udic
    -0.68
    resso
    -0.67
    POSITIVE LOGITS
    shire
    1.70
    hurst
    0.90
     Manor
    0.88
     Junction
    0.82
     Hills
    0.82
    vill
    0.76
    bridge
    0.76
     Borough
    0.75
     Town
    0.75
     Kut
    0.74
    Activations Density 0.120%

    No Known Activations