© 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
    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. 22324
    Prev
    Next
    INDEX
    Explanations

    technical terms related to servers, electronics, countries, genders, diseases, and specific products

    oai_token-act-pair · gpt-3.5-turbo

    references to technology and electronic devices

    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
     foregoing
    -0.65
    ————
    -0.59
     waking
    -0.57
     sear
    -0.54
     sque
    -0.54
     supposed
    -0.53
     such
    -0.53
    ————————
    -0.53
     joining
    -0.53
     opening
    -0.53
    POSITIVE LOGITS
    foundland
    0.88
    esses
    0.71
    eur
    0.68
    raft
    0.65
    mare
    0.63
    ussia
    0.63
    utor
    0.62
    hover
    0.61
    ween
    0.61
    vote
    0.61
    Activations Density 0.391%

    No Known Activations