© 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. 19344
    Prev
    Next
    INDEX
    Explanations

    phrases related to issuing warnings or displaying symbols requiring caution

    oai_token-act-pair · gpt-3.5-turbo

    special characters, particularly asterisks, which are often used as bullet points or indicators in lists

    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
    ivated
    -0.75
    ivating
    -0.73
     fireplace
    -0.70
    liness
    -0.66
    kson
    -0.66
     Beir
    -0.65
     lag
    -0.64
     migr
    -0.63
     delinqu
    -0.63
    azo
    -0.63
    POSITIVE LOGITS
    ERROR
    0.93
    Insert
    0.92
    AUT
    0.91
    insert
    0.89
    TEXT
    0.83
    NEW
    0.83
    Thompson
    0.81
    TON
    0.81
    laughs
    0.79
    SK
    0.79
    Activations Density 0.026%

    No Known Activations