Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7607
    Prev
    Next
    INDEX
    Explanations

    individuals based on specific criteria such as homeownership, occupations, or citizenships

    oai_token-act-pair · gpt-3.5-turbo

    phrases and clauses that reference individuals or groups defined by the word "who."

    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
     Anyway
    -0.71
    Magikarp
    -0.69
     Grip
    -0.67
    "]=>
    -0.65
     Bound
    -0.65
    interstitial
    -0.64
     Watching
    -0.64
     Camer
    -0.63
    Translation
    -0.62
     Bullet
    -0.61
    POSITIVE LOGITS
     violate
    1.20
     exceed
    1.17
     qualify
    1.14
     undergo
    1.09
     underwent
    1.03
     comply
    1.02
     exceeded
    1.00
     aren
    0.98
     wish
    0.98
     intend
    0.97
    Activations Density 0.128%

    No Known Activations