© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 14795
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the name "Gar" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Gar" in various contexts

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

    No Comments

    Negative Logits
    ĨĴ
    -0.95
    vironment
    -0.89
    terday
    -0.83
    ĸļ
    -0.82
    uyomi
    -0.77
     CPC
    -0.73
    éĹĺ
    -0.72
    hran
    -0.68
     newsp
    -0.67
    hift
    -0.67
    POSITIVE LOGITS
    bage
    1.17
    rier
    1.16
    riers
    1.00
    rets
    0.99
    raf
    0.92
    neau
    0.91
    lean
    0.86
    rod
    0.83
    ros
    0.83
    bag
    0.82
    Activations Density 0.010%

    No Known Activations