© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 13101
    Prev
    Next
    INDEX
    Explanations

    names related to "Tam" with various activation values, where the highest activation is for the name "Tam" with a value of 10

    oai_token-act-pair · gpt-3.5-turbo

    the name "Tamir" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    «ĺ
    -0.77
    ĺħ
    -0.75
    ģĸ
    -0.68
     ESC
    -0.63
     uranium
    -0.63
    Ĥª
    -0.61
     mileage
    -0.60
    creen
    -0.60
     impulse
    -0.60
     margins
    -0.59
    POSITIVE LOGITS
    pering
    1.39
    pered
    1.23
    iami
    1.03
    borgh
    1.02
    riel
    1.02
    arin
    1.01
    Tam
    0.98
    adra
    0.96
    eless
    0.96
    amo
    0.95
    Activations Density 0.037%

    No Known Activations