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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17357
    Prev
    Next
    INDEX
    Explanations

    legal terms and actions such as filing charges and imposing sanctions

    oai_token-act-pair · gpt-3.5-turbo

    statements related to legal actions and sanctions

    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
    ãĤ¡
    -0.92
    ItemThumbnailImage
    -0.78
    entimes
    -0.77
    vation
    -0.74
    antry
    -0.73
    soType
    -0.71
    aucuses
    -0.71
    ysc
    -0.70
    visible
    -0.68
    auntlet
    -0.68
    POSITIVE LOGITS
     perpetrators
    1.17
     viol
    1.16
     defendants
    1.12
     culprit
    1.07
     offenders
    1.04
     wrongdoing
    0.99
     defendant
    0.98
     negligent
    0.98
     individuals
    0.98
     convicted
    0.96
    Activations Density 0.193%

    No Known Activations