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. 4-RES-JB
    6. 12878
    Prev
    Next
    INDEX
    Explanations

    names of individuals, possibly related to sports and trades

    oai_token-act-pair · gpt-3.5-turbo

    proper names of athletes

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

    No Comments

    Negative Logits
    DragonMagazine
    -0.96
    enegger
    -0.91
     Feminist
    -0.83
    netflix
    -0.77
    20439
    -0.74
    INESS
    -0.70
    SPONSORED
    -0.69
    dress
    -0.68
     POLIT
    -0.68
     Editorial
    -0.68
    POSITIVE LOGITS
     Matthews
    0.93
     Thompson
    0.89
     undrafted
    0.89
     Rookie
    0.88
     Miller
    0.87
     teammate
    0.87
     Gron
    0.87
     athleticism
    0.86
     Allen
    0.86
     Westbrook
    0.86
    Activations Density 0.248%

    No Known Activations