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. 4218
    Prev
    Next
    INDEX
    Explanations

    legal and political terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to promises regarding legislative actions and restrictions

    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
     Randall
    -0.78
     Whitman
    -0.78
     traveled
    -0.73
     gotten
    -0.72
     Midwest
    -0.72
     folks
    -0.72
     Boone
    -0.72
     realized
    -0.70
     colorful
    -0.70
     Grape
    -0.69
    POSITIVE LOGITS
     favour
    1.06
     programme
    1.06
     favourable
    1.01
     programmes
    1.00
     licences
    0.98
     tyres
    0.96
    isation
    0.96
    Britain
    0.96
     labour
    0.95
     licence
    0.95
    Activations Density 1.232%

    No Known Activations