© 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. 4-RES-JB
    11. 6353
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal matters, specifically restraining orders and proceedings

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

    No Comments

    Negative Logits
    hra
    -0.78
    ozy
    -0.77
    imei
    -0.77
    gom
    -0.76
    ollah
    -0.76
    omics
    -0.76
    ande
    -0.74
    zz
    -0.73
    smanship
    -0.72
    opol
    -0.72
    POSITIVE LOGITS
    ŃĶ
    0.88
    ©¶æ¥µ
    0.85
    FORMATION
    0.80
     restraining
    0.76
    WIND
    0.68
     Thornton
    0.68
    IVES
    0.67
     Helm
    0.67
    Ń·
    0.66
    ãĥ¼ãĥĨãĤ£
    0.65
    Activations Density 0.026%

    No Known Activations