© 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. 17851
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific geographical location, "Kharkiv," at a high activation level

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific geographic or cultural entity associated with "Kh"

    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
    EMENT
    -0.86
    éĹĺ
    -0.82
    âĸ¬âĸ¬
    -0.74
     FANTASY
    -0.73
     Hearts
    -0.72
    FOX
    -0.72
    swick
    -0.71
     Tune
    -0.70
    manship
    -0.70
     Collider
    -0.69
    POSITIVE LOGITS
    aji
    1.15
    orn
    0.94
    orne
    0.93
    osh
    0.91
    awar
    0.90
    oj
    0.88
     Kh
    0.87
    ush
    0.87
    atch
    0.87
    azard
    0.87
    Activations Density 0.005%

    No Known Activations