Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4672
    Prev
    Next
    INDEX
    Explanations

    mentions of specific soccer players

    oai_token-act-pair · gpt-3.5-turbo

    actions related to sports, particularly in soccer

    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
     Navajo
    -0.96
     MFT
    -0.92
     DACA
    -0.87
    DAQ
    -0.83
     Millennials
    -0.81
     vacations
    -0.81
     DOE
    -0.81
     nonprofits
    -0.80
     Arpaio
    -0.79
     FOIA
    -0.78
    POSITIVE LOGITS
     manoeuv
    1.10
     defences
    1.06
     centre
    1.01
    alys
    1.00
    avour
    0.98
     favoured
    0.98
     util
    0.98
     stopp
    0.98
     defence
    0.96
     whilst
    0.96
    Activations Density 0.464%

    No Known Activations