© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 10065
    Prev
    Next
    INDEX
    Explanations

    legal and ethical violations or breaches

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to legal violations and breaches of trust or contract

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ternity
    -0.60
    asper
    -0.52
    yrics
    -0.52
     Nadu
    -0.51
    ienced
    -0.51
    foundland
    -0.51
    entle
    -0.50
    elaide
    -0.50
    inately
    -0.49
    ritten
    -0.48
    POSITIVE LOGITS
     of
    1.42
    Of
    1.31
    of
    1.22
     Of
    1.20
     thereof
    1.19
     OF
    1.16
    OF
    0.89
    oft
    0.78
    luster
    0.75
    OHN
    0.73
    Activations Density 0.777%

    No Known Activations