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. 24257
    Prev
    Next
    INDEX
    Explanations

    text structuring and formatting cues

    oai_token-act-pair · gpt-3.5-turbo

    colons and their associated textual contexts

    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
     adversaries
    -0.75
    æ©
    -0.73
     pestic
    -0.71
    ¥ŀ
    -0.71
    userc
    -0.70
    senal
    -0.69
     breakthrough
    -0.67
    phabet
    -0.67
     ingred
    -0.66
     hemor
    -0.66
    POSITIVE LOGITS
     âĨij
    0.90
     Interesting
    0.88
     Originally
    0.85
    Show
    0.85
    Originally
    0.73
     Wow
    0.72
     Hmm
    0.72
     Assuming
    0.72
    Nice
    0.68
     Surely
    0.68
    Activations Density 0.073%

    No Known Activations