© 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. 16399
    Prev
    Next
    INDEX
    Explanations

    descriptions of fights or physical confrontations

    oai_token-act-pair · gpt-3.5-turbo

    moments of success or notable achievements in 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
    itaire
    -0.81
    20439
    -0.79
    isle
    -0.77
    NEY
    -0.76
     Volunte
    -0.74
    wcsstore
    -0.73
     UCHIJ
    -0.72
    Minecraft
    -0.72
     Investig
    -0.71
    âĢİ
    -0.71
    POSITIVE LOGITS
     takedown
    1.49
     clinch
    1.46
     punches
    1.39
     choke
    1.23
     elbows
    1.20
    pperc
    1.18
     jab
    1.15
     submissions
    1.12
     submission
    1.11
     knockout
    1.09
    Activations Density 0.170%

    No Known Activations