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. 14494
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal justice, especially sentences and time spent in prison

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sentencing and incarceration in a legal context

    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
    rians
    -0.75
    phies
    -0.74
    Downloadha
    -0.62
    uscript
    -0.61
    ortun
    -0.60
    cs
    -0.59
    soDeliveryDate
    -0.59
     unlaw
    -0.57
     Remastered
    -0.56
     scrim
    -0.56
    POSITIVE LOGITS
     sentence
    1.10
     sentences
    1.03
    ishment
    0.99
     probation
    0.96
     confinement
    0.91
     imprisonment
    0.87
     prison
    0.87
    arcer
    0.82
     jail
    0.80
     sentenced
    0.78
    Activations Density 0.051%

    No Known Activations