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. 10-RES-JB
    6. 14618
    Prev
    Next
    INDEX
    Explanations

    stats and records related to sports games

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to sports game performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gang
    -0.76
    asus
    -0.68
    abulary
    -0.67
    later
    -0.65
    dinand
    -0.64
    mitt
    -0.63
    izabeth
    -0.62
    instein
    -0.61
    Austral
    -0.61
    ipedia
    -0.60
    POSITIVE LOGITS
     (.
    0.85
     against
    0.84
     totaling
    0.84
     averaging
    0.80
     matchups
    0.78
     vs
    0.75
     dating
    0.74
     featuring
    0.73
     conced
    0.73
     scoring
    0.73
    Activations Density 0.146%

    No Known Activations