© 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. 11-RES-JB
    11. 3870
    Prev
    Next
    INDEX
    Explanations

    references to the video game "Call of Duty"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Call of Duty"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bsite
    -0.73
     âĶľ
    -0.67
     filib
    -0.66
    iday
    -0.65
    acca
    -0.64
    rill
    -0.64
    ãħĭãħĭ
    -0.62
     agreeing
    -0.61
    âĶĢâĶĢ
    -0.60
     âĶľâĶĢâĶĢ
    -0.59
    POSITIVE LOGITS
     Duty
    1.46
     Cthulhu
    1.32
     Cth
    1.12
     duty
    1.08
    duty
    1.07
     Ju
    0.82
     Pri
    0.82
     Protection
    0.79
     Chern
    0.75
     Osiris
    0.73
    Activations Density 0.060%

    No Known Activations