© 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. 8-RES-JB
    11. 21772
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and occurrences of law or policy-related discussions

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to death and health statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varies
    -0.61
    ////////////////////////////////
    -0.60
    )))
    -0.59
    gencies
    -0.58
    issance
    -0.58
    ãĤ¦ãĤ¹
    -0.56
    zens
    -0.55
    deen
    -0.55
    intendent
    -0.54
    inct
    -0.54
    POSITIVE LOGITS
     unsuccessfully
    0.61
     suing
    0.59
     famously
    0.57
     mistakenly
    0.55
    FTWARE
    0.54
    otom
    0.52
     leaked
    0.51
     Yahoo
    0.50
     publicized
    0.50
     controvers
    0.50
    Activations Density 1.646%

    No Known Activations