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. 7-RES-JB
    6. 13111
    Prev
    Next
    INDEX
    Explanations

    references to legal sentences with a focus on the duration of the sentencing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to prison sentences and time served

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.79
    acly
    -0.70
    kiss
    -0.69
    ople
    -0.68
     Collider
    -0.67
    atically
    -0.67
    STER
    -0.67
    irt
    -0.67
    âĹ¼
    -0.66
    edia
    -0.66
    POSITIVE LOGITS
     imprisonment
    1.15
     probation
    1.09
     detention
    1.04
     prison
    1.03
     incarceration
    1.03
     confinement
    1.00
     jail
    0.99
     apiece
    0.96
     Detention
    0.95
     incarcer
    0.91
    Activations Density 0.057%

    No Known Activations