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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 5502
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Ward"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ward."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gdala
    -0.85
    ivia
    -0.84
    ctions
    -0.81
    urity
    -0.80
    milo
    -0.79
    berus
    -0.77
    ogene
    -0.77
    itability
    -0.77
    hedral
    -0.77
    ebus
    -0.75
    POSITIVE LOGITS
    robe
    1.52
    ages
    0.86
    hips
    0.83
    ynski
    0.83
    stown
    0.81
    ens
    0.78
    lings
    0.77
    ings
    0.77
    ner
    0.77
    ling
    0.77
    Activations Density 0.015%

    No Known Activations