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. 8-RES-JB
    6. 15304
    Prev
    Next
    INDEX
    Explanations

    initials followed by numbers and dots

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, likely athletes or celebrities, associated with initials and stats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.82
    Disclaimer
    -0.77
    ritis
    -0.73
    quartered
    -0.71
    ctr
    -0.71
    sth
    -0.71
    cens
    -0.70
    taboola
    -0.70
    SOURCE
    -0.69
     Machina
    -0.68
    POSITIVE LOGITS
     Abrams
    0.94
     Simmons
    0.85
     Walker
    0.85
     McD
    0.82
     Johnson
    0.81
     Smith
    0.81
     Phelps
    0.80
     Martinez
    0.80
     Sullivan
    0.80
     Evans
    0.79
    Activations Density 0.053%

    No Known Activations