© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 12611
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific term, possibly related to a brand or platform, which is "Ins"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "ins."

    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
    erous
    -0.65
    llan
    -0.65
    ries
    -0.65
     Sigma
    -0.64
     cha
    -0.63
     Baird
    -0.63
     distortions
    -0.61
    âĢ¢âĢ¢
    -0.58
     ÙĪ
    -0.58
     mates
    -0.57
    POSITIVE LOGITS
    urance
    1.46
    ufficient
    1.45
    omnia
    1.43
    urrection
    1.33
    ights
    1.33
    ensitive
    1.31
    iders
    1.29
    ulin
    1.27
    pect
    1.27
    ider
    1.23
    Activations Density 0.015%

    No Known Activations