© 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. 21225
    Prev
    Next
    INDEX
    Explanations

    words related to sports events and competitions

    oai_token-act-pair · gpt-3.5-turbo

    competitive outcomes and performance in sports contexts

    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
    soType
    -1.06
     Warning
    -0.73
    Fix
    -0.70
     contrace
    -0.65
     opio
    -0.61
    quickShipAvailable
    -0.61
    shut
    -0.61
     destructive
    -0.60
     repairing
    -0.60
     condol
    -0.59
    POSITIVE LOGITS
     qualify
    1.36
     win
    1.17
     earn
    1.16
     nab
    1.13
     receive
    1.11
     snag
    1.06
     qualifies
    1.05
     garner
    1.01
     ascend
    1.01
     wins
    1.00
    Activations Density 0.451%

    No Known Activations