© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5694
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people's names, possibly focusing more on a specific name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mat" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITED
    -0.68
     privileged
    -0.61
     contraception
    -0.61
     stock
    -0.60
     contraceptives
    -0.59
     turb
    -0.58
    ¥ŀ
    -0.58
     phosphate
    -0.57
    FUL
    -0.57
    ĨĴ
    -0.56
    POSITIVE LOGITS
    hematic
    1.53
    hews
    1.51
    hew
    1.43
    urity
    1.42
    hematically
    1.39
    ilda
    1.39
    ches
    1.36
    hemat
    1.30
    rox
    1.15
    terson
    1.15
    Activations Density 0.023%

    No Known Activations