© 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. 0-RES-JB
    11. 12353
    Prev
    Next
    INDEX
    Explanations

    numbers with a specific format (e.g., including special characters)

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols that represent specific values or notations in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dru
    -0.66
    outh
    -0.63
     warnings
    -0.62
    alf
    -0.60
     lately
    -0.58
     slick
    -0.57
     swearing
    -0.57
    hip
    -0.56
     whine
    -0.56
    hook
    -0.56
    POSITIVE LOGITS
     ÃĹ
    4.21
    ÃĹ
    2.30
     âĨĴ
    1.56
    âĨĴ
    1.37
     âĪĴ
    1.29
     ·
    1.19
    âĨ
    1.15
     âĨ
    1.14
    âĨij
    1.12
     x
    1.11
    Activations Density 0.008%

    No Known Activations