© 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. 11-RES-JB
    6. 21967
    Prev
    Next
    INDEX
    Explanations

    names starting with "Ge"

    oai_token-act-pair · gpt-3.5-turbo

    the mention of the name "Geoff" or variations of it, indicating a focus on this individual

    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
    INGTON
    -0.66
     intervals
    -0.64
    Interstitial
    -0.62
     pains
    -0.61
    Topic
    -0.57
     Tune
    -0.57
    TextColor
    -0.57
     declass
    -0.56
     ABE
    -0.55
     Virtue
    -0.55
    POSITIVE LOGITS
    cko
    1.38
    orget
    1.32
    ffen
    1.31
    ometry
    1.29
    ographical
    1.25
    ographically
    1.24
    orgetown
    1.19
    elong
    1.17
    isel
    1.13
    othermal
    1.11
    Activations Density 0.011%

    No Known Activations