© 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. 3-RES-JB
    11. 8188
    Prev
    Next
    INDEX
    Explanations

    mentions of a sports team

    oai_token-act-pair · gpt-3.5-turbo

    references to various teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Accessory
    -0.77
    tml
    -0.75
    lear
    -0.73
    itures
    -0.70
     guiActiveUn
    -0.69
    ibrary
    -0.69
    ifax
    -0.68
    judicial
    -0.67
    orgetown
    -0.66
    thy
    -0.65
    POSITIVE LOGITS
     mates
    1.27
    mates
    1.04
     mate
    1.01
     footballer
    0.85
     captain
    0.85
     teammates
    0.82
    rons
    0.80
     manager
    0.80
     teammate
    0.80
     captains
    0.80
    Activations Density 0.042%

    No Known Activations