© 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. 5319
    Prev
    Next
    INDEX
    Explanations

    phrases indicating cause and effect relationships

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions or phrases connecting ideas

    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
    ibble
    -0.89
    ivot
    -0.83
    ivalent
    -0.82
    conduct
    -0.82
    oof
    -0.79
     Himself
    -0.78
    incible
    -0.78
    register
    -0.76
    utch
    -0.76
    iltr
    -0.76
    POSITIVE LOGITS
     everyone
    0.89
     there
    0.88
     replaced
    0.87
     morale
    0.86
     prices
    0.84
     nobody
    0.84
     hostilities
    0.81
     everybody
    0.81
     friendships
    0.80
     pandemonium
    0.80
    Activations Density 0.225%

    No Known Activations