© 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. 22277
    Prev
    Next
    INDEX
    Explanations

    special characters or code syntax patterns like curly braces and punctuation within a text

    oai_token-act-pair · gpt-3.5-turbo

    Arabic letters or symbols

    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
    ierrez
    -0.93
    arnaev
    -0.79
    eln
    -0.78
    enegger
    -0.75
    ablishment
    -0.74
    hens
    -0.73
    anwhile
    -0.71
    uncture
    -0.70
    ographically
    -0.69
    oulos
    -0.69
    POSITIVE LOGITS
     Ø
    1.16
    ¹
    1.14
    ¨
    1.00
    Ù
    0.92
     ×
    0.88
     Ù
    0.85
    ±
    0.84
     å¤
    0.83
     Ùħ
    0.82
     اÙĦ
    0.82
    Activations Density 0.006%

    No Known Activations