© 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. 9-RES-JB
    11. 7266
    Prev
    Next
    INDEX
    Explanations

    words related to sports events, specifically football (American)

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OSP
    -0.66
    ESCO
    -0.64
    estern
    -0.61
    atalie
    -0.61
    leans
    -0.60
     arts
    -0.58
    URRENT
    -0.56
    rawdownloadcloneembedreportprint
    -0.56
     snipp
    -0.55
     retaliation
    -0.54
    POSITIVE LOGITS
    kaya
    1.21
    ourcing
    1.04
    linger
    1.02
    ourced
    0.98
    wered
    0.96
    leeve
    0.96
    ouls
    0.91
    ucker
    0.90
    avers
    0.88
    entry
    0.87
    Activations Density 0.122%

    No Known Activations