© 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. 2-RES-JB
    11. 12801
    Prev
    Next
    INDEX
    Explanations

    legal terms or phrases related to offenses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of legal offenses or crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tanz
    -0.73
    awn
    -0.65
    Oracle
    -0.65
    OHN
    -0.65
    quickShipAvailable
    -0.64
    ician
    -0.62
    ersion
    -0.62
    paren
    -0.62
     Omaha
    -0.60
     bir
    -0.60
    POSITIVE LOGITS
     offences
    1.04
     offence
    0.90
    alogue
    0.87
     offend
    0.75
    alysed
    0.74
    £
    0.72
    abulary
    0.72
    ablishment
    0.72
     NZ
    0.71
     offending
    0.70
    Activations Density 0.026%

    No Known Activations