© 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. 9-RES-JB
    11. 4305
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causality or transition between ideas

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orld
    -0.72
     sought
    -0.68
     gad
    -0.62
     dwell
    -0.60
    ortium
    -0.59
    perty
    -0.58
    farious
    -0.58
    ilee
    -0.58
    ially
    -0.58
    iste
    -0.58
    POSITIVE LOGITS
     Mahjong
    0.76
    hift
    0.74
    ï¸
    0.72
     THREE
    0.67
    ebin
    0.67
    ems
    0.67
    Plus
    0.67
    ECA
    0.66
     GOODMAN
    0.64
     Tau
    0.64
    Activations Density 0.194%

    No Known Activations