© 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. 3-RES-JB
    11. 24412
    Prev
    Next
    INDEX
    Explanations

    names of celebrities and public figures

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals, particularly celebrities and public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BLE
    -0.72
    gence
    -0.70
    leness
    -0.67
    BILITY
    -0.67
    CDC
    -0.67
    DS
    -0.66
    arter
    -0.65
    FINE
    -0.65
     Cous
    -0.65
     Franch
    -0.64
    POSITIVE LOGITS
     Manson
    1.10
    lasses
    0.99
    achev
    0.92
    urgy
    0.84
    uras
    0.84
    zsche
    0.81
    ovie
    0.79
    urus
    0.79
    ocene
    0.77
    umn
    0.76
    Activations Density 0.028%

    No Known Activations