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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 11047
    Prev
    Next
    INDEX
    Explanations

    mentions of sports achievements and statistics

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to sports statistics and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.71
    hops
    -0.71
    ornia
    -0.66
     Mehran
    -0.66
    soever
    -0.63
    isks
    -0.61
    enance
    -0.59
     Pere
    -0.59
     dstg
    -0.58
    cies
    -0.58
    POSITIVE LOGITS
    wide
    0.99
    arily
    0.89
    long
    0.74
     MVP
    0.73
     chang
    0.70
     length
    0.69
    changing
    0.67
    peat
    0.65
    izoph
    0.65
    average
    0.65
    Activations Density 0.325%

    No Known Activations