© 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. 94
    Prev
    Next
    INDEX
    Explanations

    phrases related to understanding, ideas, senses, and feelings

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to understanding or gaining insight

    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
    die
    -0.62
     Parenthood
    -0.56
    ammers
    -0.56
    vertisement
    -0.55
    oub
    -0.54
    ueller
    -0.52
     enthusi
    -0.51
     paran
    -0.51
    announced
    -0.51
    itto
    -0.49
    POSITIVE LOGITS
     of
    1.15
     how
    1.00
     thereof
    0.98
     why
    0.92
     OF
    0.92
     about
    0.86
    how
    0.86
    why
    0.84
     what
    0.84
     WHY
    0.81
    Activations Density 0.104%

    No Known Activations