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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3701
    Prev
    Next
    INDEX
    Explanations

    sentences related to legal proceedings and imprisonment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal consequences and sentencing

    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
     Uni
    -0.80
    âĹ¼
    -0.77
     Hearth
    -0.75
     Asus
    -0.73
     EntityItem
    -0.70
     Unic
    -0.70
     masc
    -0.69
    metry
    -0.69
    ãĥĨãĤ£
    -0.68
    zinski
    -0.68
    POSITIVE LOGITS
     sentencing
    2.08
     incarceration
    1.89
     sentenced
    1.86
     prison
    1.85
     incarcer
    1.83
     parole
    1.80
     convict
    1.79
     jail
    1.75
     incarcerated
    1.74
     convicted
    1.72
    Activations Density 0.803%

    No Known Activations