© 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. 11382
    Prev
    Next
    INDEX
    Explanations

    advanced technologies and features

    oai_token-act-pair · gpt-3.5-turbo

    references to advanced technology

    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
    obyl
    -0.78
    que
    -0.75
    $$$$
    -0.74
     Bundy
    -0.73
     Tycoon
    -0.72
    uku
    -0.72
    *=-
    -0.72
    onel
    -0.71
    SIZE
    -0.70
    oro
    -0.70
    POSITIVE LOGITS
     advanced
    0.83
    settings
    0.78
    enhagen
    0.77
     citiz
    0.76
     advancement
    0.75
     automation
    0.72
     espionage
    0.69
     detection
    0.69
     versions
    0.69
     forms
    0.69
    Activations Density 0.017%

    No Known Activations