© 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. 4-RES-JB
    11. 6318
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Johansen"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "John" 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
    PLIED
    -0.85
    dress
    -0.81
     subsistence
    -0.77
    20439
    -0.74
    holders
    -0.74
    uyomi
    -0.71
    ULTS
    -0.69
    anguage
    -0.65
    intendent
    -0.64
    ranean
    -0.64
    POSITIVE LOGITS
    ansson
    1.28
    ansen
    1.27
    anes
    1.04
    ani
    1.03
     Joh
    0.99
    anna
    0.93
    ans
    0.92
    onen
    0.92
    anson
    0.92
    ér
    0.90
    Activations Density 0.007%

    No Known Activations