© 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. 7-RES-JB
    11. 13929
    Prev
    Next
    INDEX
    Explanations

    names related to a specific person, in this case, "Tob" and "Cav"

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals and their associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veyard
    -0.75
    âĸ¬âĸ¬
    -0.72
     tribal
    -0.72
    interstitial
    -0.72
    fuck
    -0.70
    ufact
    -0.67
    ////////////////////////////////
    -0.66
    âĸ¬
    -0.65
    ãĤ°
    -0.65
     migr
    -0.64
    POSITIVE LOGITS
    endish
    1.02
    ijn
    0.99
    inelli
    0.96
    iolet
    0.95
    idge
    0.94
    hiba
    0.93
    asar
    0.93
    illon
    0.90
    ihara
    0.90
    illo
    0.89
    Activations Density 0.061%

    No Known Activations