© 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. 1-RES-JB
    11. 24298
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names or locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Kas" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ycle
    -0.83
     Islanders
    -0.72
    aneous
    -0.68
     Scotia
    -0.66
    ODUCT
    -0.66
     mischief
    -0.65
    ighters
    -0.65
    raught
    -0.65
     liner
    -0.63
    oured
    -0.63
    POSITIVE LOGITS
     Kas
    1.25
    imir
    1.04
    avin
    0.99
    assin
    0.96
    iewicz
    0.96
    daq
    0.88
    uga
    0.86
    avan
    0.84
    rils
    0.83
    bah
    0.82
    Activations Density 0.006%

    No Known Activations