© 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. 10-RES-JB
    11. 24023
    Prev
    Next
    INDEX
    Explanations

    invitations for feedback or input from readers

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "let us know in the comments."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •shakespeare

    No Comments

    Negative Logits
    irl
    -0.69
    ilts
    -0.64
    olitan
    -0.64
     incumb
    -0.63
    isine
    -0.61
    imble
    -0.60
    ectomy
    -0.60
    antine
    -0.60
    onomous
    -0.60
    ihad
    -0.59
    POSITIVE LOGITS
     lieu
    1.25
     regards
    1.24
     advance
    1.19
     hopes
    1.00
     anticipation
    0.99
     chronological
    0.98
     case
    0.97
     accordance
    0.96
     conjunction
    0.94
     order
    0.91
    Activations Density 0.239%

    No Known Activations