© 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. 3834
    Prev
    Next
    INDEX
    Explanations

    text related to legal matters and obligations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "by" in various contexts, indicating dependence or attribution

    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
    uality
    -0.87
    ascript
    -0.84
    puter
    -0.75
    Ì
    -0.71
    illance
    -0.70
    ival
    -0.69
    ymes
    -0.69
    ãĥ´ãĤ¡
    -0.69
    earchers
    -0.67
    ussion
    -0.67
    POSITIVE LOGITS
     virtue
    1.05
     successive
    0.82
    products
    0.78
     employers
    0.76
     contractors
    0.75
     vendors
    0.75
    laws
    0.74
     various
    0.74
     adversaries
    0.73
     those
    0.72
    Activations Density 0.152%

    No Known Activations