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. 21239
    Prev
    Next
    INDEX
    Explanations

    advice-related phrases and commands

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and separators, particularly colons and commas

    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
    cedented
    -0.79
    ELD
    -0.72
    ERY
    -0.67
    ¶æ
    -0.67
     effected
    -0.65
    Said
    -0.64
    ©¶æ¥µ
    -0.62
     Said
    -0.61
    outed
    -0.59
    ItemTracker
    -0.59
    POSITIVE LOGITS
     beware
    1.42
     try
    1.39
     prepare
    1.29
     don
    1.27
     check
    1.27
     listen
    1.25
     make
    1.21
     keep
    1.20
     consider
    1.19
     take
    1.19
    Activations Density 0.472%

    No Known Activations