© 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. 3-RES-JB
    11. 6825
    Prev
    Next
    INDEX
    Explanations

    words related to Swedish language characters

    oai_token-act-pair · gpt-3.5-turbo

    words or terms related to a specific foreign language or coding language

    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
    agonist
    -0.83
    cler
    -0.71
    idepress
    -0.69
    iazep
    -0.68
     entirety
    -0.65
     crush
    -0.65
    naires
    -0.65
     strengths
    -0.65
     carriers
    -0.63
    arily
    -0.62
    POSITIVE LOGITS
    å
    1.14
    sson
    0.90
    sb
    0.87
    ĺ
    0.86
    ø
    0.85
    borg
    0.83
    ä
    0.83
    ö
    0.83
    ¢
    0.82
    ·
    0.82
    Activations Density 0.007%

    No Known Activations