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. 19968
    Prev
    Next
    INDEX
    Explanations

    mentions of meetings

    oai_token-act-pair · gpt-3.5-turbo

    references to meetings

    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
    duc
    -0.71
    cul
    -0.70
    oil
    -0.69
    Cola
    -0.68
     srf
    -0.66
    ãģĹ
    -0.64
    ãģĦ
    -0.62
    obs
    -0.62
    incarn
    -0.62
    reverse
    -0.62
    POSITIVE LOGITS
    rooms
    1.13
    room
    1.05
     convened
    1.00
     chaired
    0.96
     session
    0.95
     meetings
    0.91
     halls
    0.89
     adjourn
    0.89
     sessions
    0.88
     attendees
    0.87
    Activations Density 0.043%

    No Known Activations