© 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. 8-RES-JB
    6. 3194
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms related to programming

    oai_token-act-pair · gpt-3.5-turbo

    references to checklist items and associated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.37
     cryptoc
    -0.36
     newsp
    -0.36
    ascript
    -0.34
     Saban
    -0.33
     pund
    -0.32
     publishing
    -0.32
     neocons
    -0.31
     editor
    -0.31
     FOIA
    -0.31
    POSITIVE LOGITS
    ãĥ¡
    0.37
    jpg
    0.35
    ãĥ¥
    0.35
     veget
    0.33
    afer
    0.32
    ²¾
    0.32
    isable
    0.31
    omorphic
    0.30
    Roaming
    0.30
     versa
    0.30
    Activations Density 3.112%

    No Known Activations