© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 20924
    Prev
    Next
    INDEX
    Explanations

    terms related to commerce and trade

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various industries and economic activities

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

    No Comments

    Negative Logits
    BUG
    -0.50
    yss
    -0.49
    âķIJâķIJ
    -0.48
    cknowled
    -0.47
    Stud
    -0.45
    oÄŁ
    -0.44
    REDACTED
    -0.43
    Sav
    -0.43
    Administ
    -0.42
    âĸ¬
    -0.42
    POSITIVE LOGITS
    hips
    1.15
    hip
    1.09
    poons
    0.92
    paces
    0.92
    pace
    0.89
    hops
    0.86
    mith
    0.83
    ourcing
    0.80
    manship
    0.80
    uits
    0.77
    Activations Density 0.865%

    No Known Activations