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

    Neuronpedia

    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. 3-RES-JB
    11. 1900
    Prev
    Next
    INDEX
    Explanations

    mentions of the last name "Hayward"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals' names, particularly in the context of events or achievements

    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
    wana
    -0.91
    inyl
    -0.87
    iegel
    -0.80
    ision
    -0.80
    ombat
    -0.79
    Ô
    -0.74
    ombo
    -0.74
    iment
    -0.73
    merce
    -0.72
    oice
    -0.72
    POSITIVE LOGITS
     Hayward
    0.79
    tree
    0.77
     Harding
    0.76
    docs
    0.76
     Fraz
    0.68
    Berry
    0.66
    breakers
    0.66
     Robotics
    0.64
    ers
    0.64
     Buccaneers
    0.63
    Activations Density 0.012%

    No Known Activations