Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 1396
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and court testimony

    oai_token-act-pair · gpt-3.5-turbo

    references to legal testimonies and witnesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yright
    -0.75
     Pixie
    -0.74
    ategory
    -0.71
     NCT
    -0.69
    FW
    -0.67
    ordinate
    -0.67
    ija
    -0.66
    mega
    -0.66
    ogo
    -0.64
    STEM
    -0.64
    POSITIVE LOGITS
     testimony
    1.29
     testimonies
    1.28
    imony
    1.03
     testify
    0.99
     testifying
    0.97
     hearings
    0.92
     testim
    0.83
     transcripts
    0.83
     witness
    0.82
     briefings
    0.81
    Activations Density 0.015%

    No Known Activations