© 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. 6-RES-JB
    11. 5526
    Prev
    Next
    INDEX
    Explanations

    health-related words like "ske" and "hel" in the context of medical or wellness situations

    oai_token-act-pair · gpt-3.5-turbo

    words related to assistance and service roles

    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
    PORT
    -0.81
    prototype
    -0.77
     Fiction
    -0.76
     Manifest
    -0.76
    FORE
    -0.76
     Dragonbound
    -0.76
    INGTON
    -0.75
     Parties
    -0.73
     Recovery
    -0.72
    Ô
    -0.72
    POSITIVE LOGITS
    teenth
    0.97
    oled
    0.96
    iced
    0.94
    inging
    0.91
    ping
    0.88
    iously
    0.87
    eyed
    0.85
    iddling
    0.83
    ips
    0.81
    pperc
    0.81
    Activations Density 0.077%

    No Known Activations