© 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 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. 2-RES-JB
    11. 501
    Prev
    Next
    INDEX
    Explanations

    occurrences of the equal sign '='

    oai_token-act-pair · gpt-4-turbo

    mathematical equations or code snippets

    oai_token-act-pair · gpt-3.5-turbo

    equality and assignment statements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emouth
    -0.88
    Ãį
    -0.79
    ixel
    -0.79
    eness
    -0.77
    soDeliveryDate
    -0.74
    endon
    -0.74
    ventures
    -0.73
    ortium
    -0.73
    alis
    -0.72
    rodu
    -0.72
    POSITIVE LOGITS
    ========
    1.38
    ============
    1.17
    ===
    0.90
     nil
    0.83
     {}
    0.81
     [];
    0.80
     0
    0.78
     False
    0.74
    equality
    0.70
     []
    0.67
    Activations Density 0.016%

    No Known Activations