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. 2124
    Prev
    Next
    INDEX
    Explanations

    comparisons using the word "as" to describe performance or achievements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the performance or role of individuals in a sporting context

    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
    claim
    -0.72
    apons
    -0.72
    romy
    -0.71
    urches
    -0.69
    oller
    -0.69
    ographers
    -0.67
    laws
    -0.66
    ools
    -0.65
    ribing
    -0.65
    ech
    -0.64
    POSITIVE LOGITS
     well
    0.88
     opposed
    0.84
     usual
    0.82
     evidenced
    0.79
     starter
    0.79
     starters
    0.78
     rookies
    0.76
     soon
    0.76
     captain
    0.75
     teammate
    0.75
    Activations Density 0.071%

    No Known Activations