© 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. 0-RES-JB
    11. 8323
    Prev
    Next
    INDEX
    Explanations

    references to touchdowns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "touchdown" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    organ
    -0.77
    pol
    -0.71
    cul
    -0.67
    olar
    -0.66
    altern
    -0.66
    Gi
    -0.63
    olic
    -0.63
    rc
    -0.62
    arine
    -0.62
    forms
    -0.61
    POSITIVE LOGITS
     touchdown
    3.43
     touchdowns
    2.59
     TDs
    1.74
     TD
    1.47
     interceptions
    1.42
     interception
    1.41
     fumble
    1.30
     kickoff
    1.24
     halftime
    1.21
     punt
    1.11
    Activations Density 0.017%

    No Known Activations