© 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. 1247
    Prev
    Next
    INDEX
    Explanations

    specific positional terms in sports, such as "shooting guard" and "outside linebacker"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations or positions in sports 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
    sett
    -0.67
    thodox
    -0.67
    views
    -0.64
    comed
    -0.64
    wallet
    -0.64
    endars
    -0.62
    ctor
    -0.62
    ratulations
    -0.62
    Property
    -0.60
    chain
    -0.60
    POSITIVE LOGITS
     halftime
    1.15
     least
    1.00
     fullback
    0.95
    las
    0.91
    onement
    0.86
     home
    0.86
    rium
    0.82
     Wembley
    0.80
    iba
    0.79
    yp
    0.79
    Activations Density 0.104%

    No Known Activations