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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 18900
    Prev
    Next
    INDEX
    Explanations

    mentions of statistics related to American football, particularly sacks made by players

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sacks in football

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EB
    -0.64
     locality
    -0.63
    estine
    -0.63
    assies
    -0.63
    ependence
    -0.62
    Dub
    -0.61
    issance
    -0.61
    rina
    -0.60
    ternity
    -0.60
    ertain
    -0.60
    POSITIVE LOGITS
    tackle
    0.88
     sacks
    0.87
    sung
    0.85
     sack
    0.83
    acks
    0.78
    oppable
    0.76
    ukong
    0.68
     tackles
    0.68
    acked
    0.66
    bery
    0.66
    Activations Density 0.023%

    No Known Activations