© 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. 7515
    Prev
    Next
    INDEX
    Explanations

    proper names and titles within text

    oai_token-act-pair · gpt-3.5-turbo

    specific letters, characters, or symbols in a sequence

    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
     Dalton
    -0.86
     Kem
    -0.83
     ende
    -0.81
     Jal
    -0.79
     Cameron
    -0.78
     millenn
    -0.77
    terday
    -0.77
     JP
    -0.74
     Catal
    -0.72
     Trin
    -0.72
    POSITIVE LOGITS
    ogg
    1.05
    unk
    1.00
    ank
    0.99
    plex
    0.93
    ark
    0.93
    anks
    0.90
    arp
    0.90
    flex
    0.88
    mb
    0.87
    insk
    0.87
    Activations Density 0.156%

    No Known Activations