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. 7-RES-JB
    6. 17011
    Prev
    Next
    INDEX
    Explanations

    sports events and scores

    oai_token-act-pair · gpt-3.5-turbo

    information related to sports events and scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acea
    -0.85
    oros
    -0.77
    Journal
    -0.73
     Occupations
    -0.72
    adata
    -0.72
    hari
    -0.69
    DragonMagazine
    -0.69
     brim
    -0.68
    sheet
    -0.68
    andowski
    -0.66
    POSITIVE LOGITS
     Showdown
    0.88
     finals
    0.88
     rematch
    0.86
     semifinals
    0.86
     Finals
    0.82
     scrimmage
    0.77
     semif
    0.76
     finale
    0.73
    venge
    0.71
    Final
    0.70
    Activations Density 0.207%

    No Known Activations