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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14798
    Prev
    Next
    INDEX
    Explanations

    names containing the letters "Sp" followed by either the digit 10, 9, or 8

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific name or reference related to individuals or entities

    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
     defaults
    -0.68
     resting
    -0.66
    İĭ
    -0.64
     separatist
    -0.63
     tid
    -0.63
     BT
    -0.61
     competitiveness
    -0.59
     fusion
    -0.58
     default
    -0.58
     labor
    -0.57
    POSITIVE LOGITS
    atial
    1.36
    aghetti
    1.36
    auld
    1.28
    encers
    1.27
    ruce
    1.27
    angler
    1.26
    okes
    1.23
    herical
    1.22
    otted
    1.22
    urred
    1.22
    Activations Density 0.016%

    No Known Activations