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. 20911
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and political events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant events and their consequences

    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
    scribe
    -0.83
    resents
    -0.78
    pose
    -0.72
     Contains
    -0.71
    breaker
    -0.71
    esting
    -0.71
    arah
    -0.69
    ACH
    -0.69
    obook
    -0.68
    ersed
    -0.68
    POSITIVE LOGITS
     Soon
    0.94
     tensions
    0.85
     Suddenly
    0.83
     friendships
    0.83
     pandemonium
    0.82
     hostilities
    0.80
     tens
    0.80
     normalized
    0.80
     revolutions
    0.79
     eventually
    0.78
    Activations Density 0.394%

    No Known Activations