Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20105
    Prev
    Next
    INDEX
    Explanations

    phrases related to fighter jets in military contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific military aircraft programs

    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
     pim
    -0.69
    steen
    -0.66
     adjourn
    -0.64
     brim
    -0.63
     ske
    -0.63
     Poké
    -0.63
     cous
    -0.63
     charact
    -0.62
     synd
    -0.60
     scr
    -0.60
    POSITIVE LOGITS
    35
    1.02
    series
    1.01
    Series
    0.96
    117
    0.95
    Zero
    0.93
    350
    0.91
    Secure
    0.91
    Unit
    0.90
    150
    0.90
    111
    0.90
    Activations Density 0.030%

    No Known Activations