© 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. 10-RES-JB
    11. 20471
    Prev
    Next
    INDEX
    Explanations

    mentions of different sports leagues and competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to sports and athletics

    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
    imov
    -0.74
    vable
    -0.72
     Lerner
    -0.72
     Canaver
    -0.71
     Helpful
    -0.70
     EntityItem
    -0.68
    vae
    -0.67
    eware
    -0.66
     Publishers
    -0.65
    available
    -0.64
    POSITIVE LOGITS
     career
    1.40
     counterpart
    1.30
     upbringing
    1.29
     ambitions
    1.28
     counterparts
    1.26
     buddies
    1.23
     colleague
    1.23
     girlfriend
    1.23
     persona
    1.22
     stint
    1.21
    Activations Density 0.520%

    No Known Activations