© 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. 11-RES-JB
    11. 6679
    Prev
    Next
    INDEX
    Explanations

    references to specific entities, organizations, and numbers within text

    oai_token-act-pair · gpt-3.5-turbo

    references to institutions and their actions

    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
     earlier
    -0.78
     at
    -0.77
     elsewhere
    -0.72
     therein
    -0.69
     later
    -0.64
     shortly
    -0.63
     in
    -0.63
    agraph
    -0.62
     early
    -0.62
     backstage
    -0.62
    POSITIVE LOGITS
    DragonMagazine
    0.74
    76561
    0.63
    itzer
    0.60
     confir
    0.56
    bred
    0.55
     partName
    0.54
     thanked
    0.53
    oland
    0.53
     sqor
    0.52
    tested
    0.51
    Activations Density 1.090%

    No Known Activations