© 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. 11-RES-JB
    11. 308
    Prev
    Next
    INDEX
    Explanations

    text related to legal proceedings and requirements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Miko
    -0.77
    peror
    -0.74
    ãĤ¼
    -0.72
    ahime
    -0.69
    ripp
    -0.69
    Theme
    -0.67
     trending
    -0.67
    ¥µ
    -0.67
     Floating
    -0.66
     Expansion
    -0.66
    POSITIVE LOGITS
     consent
    1.48
     testify
    1.44
     incrim
    1.38
     comply
    1.29
     confess
    1.26
     disclose
    1.24
     cooperate
    1.23
     Consent
    1.22
     voluntarily
    1.22
     plead
    1.16
    Activations Density 0.502%

    No Known Activations