© 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. 3100
    Prev
    Next
    INDEX
    Explanations

    soccer match results

    oai_token-act-pair · gpt-3.5-turbo

    key statistics related to sports scores and highlights

    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
     blending
    -0.74
    milo
    -0.73
     treatments
    -0.71
     quir
    -0.71
     footing
    -0.70
     therap
    -0.69
     macros
    -0.69
    erred
    -0.69
     explan
    -0.69
    umatic
    -0.68
    POSITIVE LOGITS
     Wolves
    0.83
     Sidney
    0.83
     Tigers
    0.82
     Petr
    0.80
     Recap
    0.79
     Ivan
    0.76
     Timbers
    0.75
     Chiefs
    0.74
     Bye
    0.73
     Sasha
    0.71
    Activations Density 0.086%

    No Known Activations