© 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. 6-RES-JB
    11. 532
    Prev
    Next
    INDEX
    Explanations

    names or parts of names that contain the string "Lar"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names that start with "Lar," "Lor," or "Lac."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CRIP
    -0.97
    manship
    -0.96
    ãģ®éŃĶ
    -0.91
    éĹĺ
    -0.87
    士
    -0.82
    代
    -0.69
    ħĭ
    -0.69
    âĶĢâĶĢ
    -0.65
    EY
    -0.63
    ĨĴ
    -0.63
    POSITIVE LOGITS
    acy
    0.93
    abee
    0.92
    imore
    0.91
    vae
    0.91
    issa
    0.90
    abit
    0.86
    acial
    0.85
    ousse
    0.83
    pole
    0.82
    acan
    0.81
    Activations Density 0.036%

    No Known Activations