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. 10-RES-JB
    6. 4014
    Prev
    Next
    INDEX
    Explanations

    information related to legal trials, convictions, and sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to legal proceedings and capital punishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.87
     Ivanka
    -0.73
     patches
    -0.69
     "#
    -0.69
    paces
    -0.68
     newsletters
    -0.67
     contacting
    -0.66
    mone
    -0.66
    rir
    -0.65
     staffing
    -0.65
    POSITIVE LOGITS
     jury
    1.40
     verdict
    1.31
     Jury
    1.28
     convict
    1.21
    Judge
    1.21
     sentenced
    1.19
     sentencing
    1.19
     conviction
    1.16
     acquitted
    1.15
     guilty
    1.12
    Activations Density 0.235%

    No Known Activations