© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11071
    Prev
    Next
    INDEX
    Explanations

    mentions of sports achievements and titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of sports achievements and championships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    react
    -0.80
    monitor
    -0.76
    Monitor
    -0.76
    tone
    -0.75
    ãĥ¤
    -0.74
    Snap
    -0.69
    Phones
    -0.67
    radio
    -0.64
    staff
    -0.64
    rouse
    -0.64
    POSITIVE LOGITS
     consecutive
    0.87
     consecut
    0.86
     Winners
    0.81
     convinc
    0.80
     twice
    0.80
     prestigious
    0.80
     renown
    0.78
     Cald
    0.78
     championships
    0.78
     qualifier
    0.78
    Activations Density 0.366%

    No Known Activations