© 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. 0-RES-JB
    11. 6877
    Prev
    Next
    INDEX
    Explanations

    references to locations or regions with 'Strip' in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to "Strip," particularly in a geographical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otin
    -0.70
     AD
    -0.70
    ability
    -0.67
    amy
    -0.63
     ag
    -0.63
     ka
    -0.61
    AD
    -0.61
     om
    -0.60
     tea
    -0.59
    able
    -0.58
    POSITIVE LOGITS
     Strip
    4.48
    strip
    2.11
     strip
    2.02
     Stri
    1.40
     strips
    1.38
     stripes
    1.22
     striped
    1.11
     stripe
    1.09
    stri
    0.95
     Wasteland
    0.95
    Activations Density 0.015%

    No Known Activations