© 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. 7-RES-JB
    11. 12668
    Prev
    Next
    INDEX
    Explanations

    references to a person's age, particularly 'old' with different intensities

    oai_token-act-pair · gpt-3.5-turbo

    references to age, particularly the word "old" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ń·
    -0.95
    inventoryQuantity
    -0.89
    ascript
    -0.87
     mathemat
    -0.84
    Ĥİ
    -0.83
    oldown
    -0.81
    vernment
    -0.79
    icter
    -0.79
    ipedia
    -0.79
    ©¶æ
    -0.78
    POSITIVE LOGITS
     Frenchman
    0.93
     woman
    0.85
     Romanian
    0.82
     Swiss
    0.80
     man
    0.79
     Spani
    0.78
     Indonesian
    0.77
     Bulgarian
    0.77
     Filipino
    0.77
     Mississ
    0.77
    Activations Density 0.043%

    No Known Activations