© 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. 6-RES-JB
    11. 2987
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and court appearances

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ui" associated with various statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inosaur
    -0.79
    itude
    -0.79
     skelet
    -0.73
    sylvania
    -0.70
    ioned
    -0.69
    ividual
    -0.64
    thouse
    -0.63
    look
    -0.63
     ramps
    -0.63
    heimer
    -0.62
    POSITIVE LOGITS
    owa
    0.97
    isine
    0.91
    hei
    0.88
    ÃŁ
    0.87
    jing
    0.84
    obile
    0.83
    qq
    0.82
    utenant
    0.81
    qa
    0.81
    selage
    0.79
    Activations Density 0.026%

    No Known Activations