© 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. 10-RES-JB
    11. 8554
    Prev
    Next
    INDEX
    Explanations

    statistics or scores related to sports

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and scores related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    use
    -0.65
    icus
    -0.61
    bara
    -0.61
    perse
    -0.60
    equality
    -0.58
    communication
    -0.58
    hai
    -0.57
    don
    -0.55
    arton
    -0.53
    grave
    -0.53
    POSITIVE LOGITS
     overall
    0.84
     (.
    0.83
     underdog
    0.77
     record
    0.77
    owship
    0.74
     Overall
    0.70
     Record
    0.70
    iversal
    0.69
     Records
    0.69
     FG
    0.68
    Activations Density 0.045%

    No Known Activations