© 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. 4-RES-JB
    11. 1335
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names like "Tamir" and variations

    oai_token-act-pair · gpt-3.5-turbo

    the name "Tam" in various contexts

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

    No Comments

    Negative Logits
     mileage
    -0.80
     unchecked
    -0.73
    ģĸ
    -0.70
    ĺħ
    -0.67
     uranium
    -0.66
    ĻĤ
    -0.66
     tremend
    -0.66
     commissions
    -0.65
     anecd
    -0.64
    eering
    -0.64
    POSITIVE LOGITS
    Tam
    1.21
    pering
    1.20
    pered
    1.13
    borgh
    1.01
    my
    0.95
    eless
    0.94
    iami
    0.93
    ás
    0.93
    neys
    0.89
    ara
    0.89
    Activations Density 0.007%

    No Known Activations