© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11513
    Prev
    Next
    INDEX
    Explanations

    numerical patterns or sequences

    oai_token-act-pair · gpt-3.5-turbo

    various forms of numerals or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.89
     rul
    -0.70
     1945
    -0.68
     1895
    -0.66
     455
    -0.65
    otti
    -0.64
    usters
    -0.64
     265
    -0.64
     165
    -0.62
     1905
    -0.62
    POSITIVE LOGITS
    8
    1.26
    78
    0.94
     8
    0.94
    808
    0.93
    08
    0.92
     VIII
    0.82
    eight
    0.80
    768
    0.78
    748
    0.78
    088
    0.77
    Activations Density 0.068%

    No Known Activations