© 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. 24475
    Prev
    Next
    INDEX
    Explanations

    the name "Krzanich"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "zan" in various contexts

    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
    racted
    -0.68
    growth
    -0.67
     confir
    -0.63
    susp
    -0.62
     mileage
    -0.62
     outgoing
    -0.62
    ilde
    -0.61
     plur
    -0.60
     Limits
    -0.60
     peripher
    -0.59
    POSITIVE LOGITS
    zan
    1.16
    omon
    0.99
    ning
    0.90
    atown
    0.87
    amac
    0.86
    thal
    0.84
    ita
    0.82
    owski
    0.82
    sey
    0.82
    anu
    0.81
    Activations Density 0.006%

    No Known Activations