© 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. 2986
    Prev
    Next
    INDEX
    Explanations

    video identifiers

    oai_token-act-pair · gpt-3.5-turbo

    references to videos and video-related content

    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
     Tomb
    -0.69
     meanwhile
    -0.68
     orchestr
    -0.66
    ichick
    -0.65
     Tsukuyomi
    -0.61
     Nights
    -0.61
    ²
    -0.60
     orche
    -0.60
     Fortress
    -0.59
    uton
    -0.59
    POSITIVE LOGITS
    GREEN
    0.93
    Warning
    0.76
    CLE
    0.76
    DES
    0.75
    LOS
    0.73
    prev
    0.72
    EV
    0.72
    WARNING
    0.72
    VOL
    0.72
    Researchers
    0.72
    Activations Density 0.133%

    No Known Activations