© 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. 12016
    Prev
    Next
    INDEX
    Explanations

    phrases related to fitting or compatibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to suitability or compatibility

    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
    cember
    -0.71
    escal
    -0.70
    icide
    -0.62
    EED
    -0.62
    yard
    -0.59
    affer
    -0.58
    posure
    -0.58
    urance
    -0.57
    icult
    -0.57
    ursor
    -0.56
    POSITIVE LOGITS
     snug
    1.36
     neatly
    1.15
     into
    1.11
     comfortably
    1.08
     perfectly
    1.02
     seamlessly
    1.01
     squarely
    0.98
     nicely
    0.94
     onto
    0.92
    gerald
    0.86
    Activations Density 0.087%

    No Known Activations