© 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. 7-RES-JB
    11. 24212
    Prev
    Next
    INDEX
    Explanations

    terms related to wrestling and physical confrontation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    verbs related to physical struggle or competition

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uten
    -0.75
    arial
    -0.69
    ################
    -0.66
     sunshine
    -0.62
     Centauri
    -0.62
    nah
    -0.60
    ATES
    -0.60
    GE
    -0.60
    ctuary
    -0.60
    uren
    -0.60
    POSITIVE LOGITS
    restling
    1.07
    enegger
    0.89
     wrestle
    0.88
     wrestling
    0.76
    mania
    0.75
     Jiu
    0.75
     Wrest
    0.74
    bowl
    0.73
    keye
    0.72
    weed
    0.72
    Activations Density 0.023%

    No Known Activations