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. 8-RES-JB
    6. 17433
    Prev
    Next
    INDEX
    Explanations

    phrases related to commenting on various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to commenting or making statements about events or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bia
    -0.85
    Rail
    -0.75
    ayne
    -0.68
    çͰ
    -0.68
    trak
    -0.67
    CHAT
    -0.67
    aye
    -0.65
    raq
    -0.65
    çīĪ
    -0.64
    chat
    -0.64
    POSITIVE LOGITS
     dictators
    0.82
     deadlines
    0.80
     crises
    0.77
     surprises
    0.77
     endings
    0.72
     unve
    0.71
     storytelling
    0.70
     acron
    0.70
     reinvent
    0.70
     mistakes
    0.69
    Activations Density 1.329%

    No Known Activations