© 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. 3685
    Prev
    Next
    INDEX
    Explanations

    details related to weight classes and fighting competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to weight classes and titles in combat 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
     ACPI
    -0.72
    Newsletter
    -0.72
    Recomm
    -0.71
    ulhu
    -0.68
     Computing
    -0.67
     Legisl
    -0.66
     UNCLASSIFIED
    -0.66
    arity
    -0.66
    aceae
    -0.65
    20439
    -0.65
    POSITIVE LOGITS
     bout
    1.28
     rematch
    1.22
    UFC
    1.16
     bouts
    1.15
     MMA
    1.15
    weight
    1.13
    fight
    1.07
     UFC
    1.04
    nen
    1.03
     fight
    1.01
    Activations Density 0.152%

    No Known Activations