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. 11-RES-JB
    6. 16974
    Prev
    Next
    INDEX
    Explanations

    the prefix "ins" or "Ins" in words

    oai_token-act-pair · gpt-3.5-turbo

    references to "insider" perspectives or insights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Archdemon
    -0.64
     RTX
    -0.61
     Baird
    -0.60
     Sao
    -0.60
     Reconstruction
    -0.60
     Sigma
    -0.60
    erous
    -0.58
     Libraries
    -0.57
     Remastered
    -0.57
     McAuliffe
    -0.57
    POSITIVE LOGITS
    urance
    1.56
    ufficient
    1.56
    omnia
    1.53
    pection
    1.47
    iders
    1.46
    urrection
    1.43
    ights
    1.42
    ensitive
    1.42
    ulin
    1.42
    ider
    1.36
    Activations Density 0.030%

    No Known Activations