© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 272
    Prev
    Next
    INDEX
    Explanations

    sentences mentioning legal sentencing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sentencing and prison terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.69
    âĹ¼
    -0.66
     Franch
    -0.63
     Grail
    -0.63
    çļ
    -0.62
    btn
    -0.60
    wcsstore
    -0.60
    uum
    -0.60
     Bride
    -0.59
    TPPStreamerBot
    -0.59
    POSITIVE LOGITS
     probation
    1.07
     prison
    1.06
     jail
    1.03
     imprisonment
    1.00
     death
    0.96
     confinement
    0.94
     incarceration
    0.93
     serve
    0.89
     life
    0.89
     spend
    0.89
    Activations Density 0.055%

    No Known Activations