© 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. 1751
    Prev
    Next
    INDEX
    Explanations

    terms related to sports, specifically focused on field goals

    oai_token-act-pair · gpt-3.5-turbo

    references to "field goals" in a sports context

    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
    ilyn
    -0.72
    bian
    -0.70
    éĹĺ
    -0.69
     Reich
    -0.68
    ILA
    -0.68
     ABE
    -0.68
     Seas
    -0.67
     UTC
    -0.67
     Paste
    -0.65
    itarian
    -0.65
    POSITIVE LOGITS
    plane
    0.86
    field
    0.86
    keepers
    0.80
    ilage
    0.80
    fields
    0.79
    keeping
    0.78
    keeper
    0.78
    locked
    0.78
    ers
    0.76
     turf
    0.74
    Activations Density 0.025%

    No Known Activations