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. 22355
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Tyson"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the individual named Tyson

    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
    âĵĺ
    -0.71
    Scotland
    -0.70
    UGE
    -0.69
    76561
    -0.69
    teen
    -0.68
    ãĥĥãĥĪ
    -0.68
    stract
    -0.68
    oppers
    -0.67
    ugal
    -0.66
    tesy
    -0.65
    POSITIVE LOGITS
     Foods
    1.04
     Tyson
    1.02
    yson
    0.88
     Chandler
    0.86
     Apost
    0.77
    onson
    0.76
     Vaughn
    0.72
     Summers
    0.70
    ertodd
    0.70
    imus
    0.68
    Activations Density 0.005%

    No Known Activations