© 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. 11-RES-JB
    11. 2623
    Prev
    Next
    INDEX
    Explanations

    sports-related events or actions on a soccer field, such as crosses, shots, goals, and penalties

    oai_token-act-pair · gpt-3.5-turbo

    actions and events related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zos
    -0.74
    OUP
    -0.65
     Flavoring
    -0.64
     marriages
    -0.63
     raids
    -0.62
    sbm
    -0.61
     epidem
    -0.58
     educ
    -0.57
     Investigations
    -0.57
     acron
    -0.56
    POSITIVE LOGITS
     zone
    0.97
     circle
    0.85
     stripe
    0.85
     corner
    0.84
     blocker
    0.83
     wall
    0.82
     vacated
    0.81
     line
    0.81
    zone
    0.81
     barrier
    0.81
    Activations Density 0.121%

    No Known Activations