© 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. 6-RES-JB
    11. 7796
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Issa" along with some context such as geographical location or political position

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and places, particularly focusing on the name "Issa"

    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
    stones
    -0.79
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.73
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.72
    stone
    -0.71
    matically
    -0.70
    orem
    -0.64
    eries
    -0.64
    oric
    -0.62
     jelly
    -0.62
    wash
    -0.62
    POSITIVE LOGITS
    idan
    0.85
    arez
    0.74
    iah
    0.74
    eki
    0.73
    sha
    0.71
    eye
    0.69
    uary
    0.69
     Rash
    0.69
     Issa
    0.68
    unta
    0.68
    Activations Density 0.070%

    No Known Activations