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. 10-RES-JB
    6. 21286
    Prev
    Next
    INDEX
    Explanations

    brand names or specific entities

    oai_token-act-pair · gpt-3.5-turbo

    specific product or brand names

    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
    •San
    #5 activation: 5.77

    No Comments

    Negative Logits
    âĢķ
    -0.63
    âĢ¢âĢ¢
    -0.61
    ––
    -0.61
    *.
    -0.61
     accompanied
    -0.60
    }.
    -0.58
    .*
    -0.58
     respons
    -0.57
     â̦"
    -0.57
     inst
    -0.56
    POSITIVE LOGITS
    Coin
    0.80
    Eye
    0.78
    Berry
    0.78
    Wire
    0.75
    isoft
    0.74
    Bot
    0.73
    Wing
    0.72
    coin
    0.72
    Fest
    0.71
    Sync
    0.71
    Activations Density 0.546%

    No Known Activations