© 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. 4-RES-JB
    11. 19379
    Prev
    Next
    INDEX
    Explanations

    phrases related to teamwork and sports

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams, specifically their performance and context in games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tml
    -0.76
     drip
    -0.72
    ibrary
    -0.70
    à¼
    -0.69
    sbm
    -0.69
    Accessory
    -0.69
    ãģ¦
    -0.68
     ILCS
    -0.68
    ¿½
    -0.67
    brew
    -0.66
    POSITIVE LOGITS
     mates
    1.13
    mates
    0.92
     mate
    0.89
     manager
    0.82
     colours
    0.82
     captain
    0.82
     footballer
    0.82
    rons
    0.78
     Colomb
    0.77
     Barcelona
    0.74
    Activations Density 0.039%

    No Known Activations