© 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. 1-RES-JB
    11. 9582
    Prev
    Next
    INDEX
    Explanations

    internal issues or references within a system or organization

    oai_token-act-pair · gpt-3.5-turbo

    references to internal structures or processes within organizations or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apo
    -0.90
     Frog
    -0.79
    ammy
    -0.77
    kers
    -0.69
    vous
    -0.68
    vich
    -0.67
    KI
    -0.67
    Bring
    -0.64
    LOS
    -0.63
     Pose
    -0.63
    POSITIVE LOGITS
     workings
    1.04
     combustion
    1.03
     internal
    0.98
     organs
    0.92
     Internal
    0.89
     affairs
    0.85
     internally
    0.79
     deliberations
    0.78
    ãĤ¢ãĥ«
    0.76
    ãĥĥãĥī
    0.74
    Activations Density 0.009%

    No Known Activations