© 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. 20921
    Prev
    Next
    INDEX
    Explanations

    words related to time units and numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letters "ar" or "AR" within words

    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
    ĸļ
    -0.88
    ĨĴ
    -0.82
    assetsadobe
    -0.72
    ¬¼
    -0.70
    代
    -0.69
    éĹĺ
    -0.69
     Nicotine
    -0.69
     Nug
    -0.67
    erker
    -0.65
    EStream
    -0.62
    POSITIVE LOGITS
    riage
    1.12
    acters
    1.08
    acter
    1.01
    thur
    1.01
    ithmetic
    1.01
    allel
    0.93
    riors
    0.92
    bor
    0.91
    beit
    0.90
    riages
    0.86
    Activations Density 0.036%

    No Known Activations