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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 9206
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Harvey"

    oai_token-act-pair · gpt-3.5-turbo

    references to Hurricane Harvey

    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
    nesota
    -0.99
    76561
    -0.83
    */(
    -0.82
    REDACTED
    -0.81
    monary
    -0.80
    opsy
    -0.77
    ItemTracker
    -0.74
    cius
    -0.72
    udic
    -0.71
    ularity
    -0.71
    POSITIVE LOGITS
     Weinstein
    1.26
     Harvey
    1.05
     Milk
    0.97
     Nichols
    0.89
     Dent
    0.82
    bugs
    0.77
     Feldman
    0.75
     Moore
    0.73
     Lank
    0.73
     Irma
    0.66
    Activations Density 0.009%

    No Known Activations