© 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. 8-RES-JB
    11. 23533
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports games and players

    oai_token-act-pair · gpt-3.5-turbo

    numeric statistics related to games played

    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
    ortium
    -0.68
     Catalyst
    -0.66
    aptic
    -0.62
     decree
    -0.62
     incorporation
    -0.61
     submitting
    -0.60
     landfall
    -0.60
     Cosmic
    -0.59
     toppled
    -0.59
     Expend
    -0.59
    POSITIVE LOGITS
     consecut
    0.81
     professionally
    0.77
     concurrently
    0.77
     innings
    0.76
     differently
    0.75
    intensive
    0.75
     extensively
    0.74
    thin
    0.74
    secut
    0.73
    heartedly
    0.73
    Activations Density 0.504%

    No Known Activations