© 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 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. 15970
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement, specifically the act of going up and down

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate movement or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    icans
    -0.74
    DOS
    -0.72
    chlor
    -0.71
    icus
    -0.71
    ogi
    -0.70
    atl
    -0.70
    inn
    -0.70
    atis
    -0.68
    resa
    -0.67
    ariat
    -0.67
    POSITIVE LOGITS
     depending
    1.04
     alike
    0.87
     throughout
    0.83
     respectively
    0.81
     movements
    0.79
     interchange
    0.77
     altern
    0.76
     unpredict
    0.75
     directions
    0.74
    )=(
    0.73
    Activations Density 0.127%

    No Known Activations