© 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. 10-RES-JB
    11. 17482
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to sentencing

    oai_token-act-pair · gpt-3.5-turbo

    references to legal sentences and penalties

    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
    BLIC
    -0.79
    chio
    -0.71
    thora
    -0.71
    ergy
    -0.70
    akery
    -0.69
    ãĤ¤ãĥĪ
    -0.69
     Owners
    -0.68
    chu
    -0.67
    uca
    -0.67
    ãĤ¶
    -0.66
    POSITIVE LOGITS
     sentences
    1.22
     sentencing
    1.13
     sentence
    1.11
     imposed
    1.01
     convict
    0.94
     sentenced
    0.85
     probation
    0.84
     prison
    0.83
     abolition
    0.80
     inflicted
    0.79
    Activations Density 0.070%

    No Known Activations