© 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. 20637
    Prev
    Next
    INDEX
    Explanations

    requests for feedback or comments

    oai_token-act-pair · gpt-3.5-turbo

    interactions related to user engagement and enjoyment

    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
     cumbers
    -0.67
    GV
    -0.67
    eteenth
    -0.65
    ylum
    -0.63
    ©¶æ¥µ
    -0.61
    judicial
    -0.59
    rugged
    -0.58
     century
    -0.58
    reth
    -0.58
    adr
    -0.58
    POSITIVE LOGITS
     yourselves
    0.94
     THIS
    0.89
     my
    0.89
     this
    0.89
     THESE
    0.87
     anything
    0.86
     me
    0.84
     these
    0.83
     :)
    0.79
    endum
    0.79
    Activations Density 0.218%

    No Known Activations