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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 13990
    Prev
    Next
    INDEX
    Explanations

    names related to specific individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kaufman" and related names in various contexts

    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
     Cavaliers
    -0.72
     crush
    -0.68
    antly
    -0.63
    ordinary
    -0.63
    aneously
    -0.62
    ISIS
    -0.61
     Revelations
    -0.60
    eat
    -0.59
     Underworld
    -0.59
    Rated
    -0.59
    POSITIVE LOGITS
    sonian
    0.96
    icter
    0.91
    kson
    0.88
    gren
    0.88
    mination
    0.86
    emark
    0.86
    iversal
    0.84
    jriwal
    0.81
    mbuds
    0.80
    conservancy
    0.78
    Activations Density 0.022%

    No Known Activations