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. 11-RES-JB
    6. 19404
    Prev
    Next
    INDEX
    Explanations

    dates and events in a news context

    oai_token-act-pair · gpt-3.5-turbo

    instances of high-impact events or their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dilig
    -0.84
     metic
    -0.82
     nodd
    -0.82
     oun
    -0.78
     incent
    -0.75
     cigar
    -0.74
    aditional
    -0.74
    ¥ŀ
    -0.74
     warr
    -0.73
     deflation
    -0.71
    POSITIVE LOGITS
    She
    2.78
    Her
    2.52
    she
    2.26
    Ms
    2.05
    Mrs
    1.87
     she
    1.66
    Woman
    1.66
    Women
    1.66
     She
    1.61
     her
    1.60
    Activations Density 0.319%

    No Known Activations