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. 22190
    Prev
    Next
    INDEX
    Explanations

    references to specific institutions and locations, especially related to education or culture

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions and their related fields

    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
    worms
    -0.91
    keyes
    -0.84
    storms
    -0.84
    laughter
    -0.82
    weed
    -0.80
    drawn
    -0.78
     wand
    -0.78
    wal
    -0.77
    mine
    -0.76
    obin
    -0.74
    POSITIVE LOGITS
     Directorate
    1.06
     Organisation
    1.04
     Franç
    1.00
     Instit
    0.98
     Institution
    0.96
     Confederation
    0.94
     Organization
    0.94
     Volks
    0.93
     Association
    0.93
     Libre
    0.91
    Activations Density 0.227%

    No Known Activations