© 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. 7-RES-JB
    11. 21230
    Prev
    Next
    INDEX
    Explanations

    sentences ending with specific formatting symbols

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific symbol sequences or patterns represented by "âĢ"

    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
    wagen
    -0.71
     Samar
    -0.70
     multiplying
    -0.69
     touches
    -0.67
    nesday
    -0.66
     municipality
    -0.65
     multiplied
    -0.65
     furthe
    -0.63
     shroud
    -0.63
    abwe
    -0.62
    POSITIVE LOGITS
    £
    1.14
    º
    1.13
    ¹
    1.07
    ¡
    1.04
    »
    1.02
    ®
    1.02
    ¬
    1.00
    Į
    0.98
    ł
    0.98
    ľ
    0.97
    Activations Density 0.138%

    No Known Activations