© 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. 11-RES-JB
    11. 14368
    Prev
    Next
    INDEX
    Explanations

    phrases related to knowledge and understandings

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating knowledge and understanding of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teasp
    -0.96
    riott
    -0.79
    odder
    -0.78
    oaded
    -0.78
    retty
    -0.78
    erity
    -0.76
    ratulations
    -0.75
    vertisement
    -0.74
    appointed
    -0.73
    reau
    -0.71
    POSITIVE LOGITS
     how
    1.30
     why
    1.12
     anatomy
    1.06
     what
    1.02
     genetics
    1.01
     WHY
    0.97
     physiology
    0.96
     psychology
    0.96
     economics
    0.95
     geography
    0.94
    Activations Density 0.192%

    No Known Activations