© 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. 1-RES-JB
    11. 24061
    Prev
    Next
    INDEX
    Explanations

    references to specific soccer leagues, specifically the USL and AHL

    oai_token-act-pair · gpt-3.5-turbo

    references to various professional soccer leagues and their associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hair
    -0.79
    rod
    -0.76
    travel
    -0.76
    away
    -0.73
    egg
    -0.73
    frame
    -0.73
    ration
    -0.73
    wal
    -0.71
    policy
    -0.70
    rule
    -0.70
    POSITIVE LOGITS
     USL
    1.09
    MpServer
    0.78
     glim
    0.77
     AHL
    0.76
    GBT
    0.74
     NASL
    0.73
    ONSORED
    0.72
    ategory
    0.72
    PDATE
    0.70
    escent
    0.69
    Activations Density 0.007%

    No Known Activations