© 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. 11-RES-JB
    11. 7012
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal consequences and prosecution

    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
     Leap
    -0.64
     Knot
    -0.64
     optimism
    -0.62
    ggles
    -0.62
     Cutter
    -0.62
     Surviv
    -0.62
     Remastered
    -0.61
     vantage
    -0.60
     Miracle
    -0.60
    angular
    -0.60
    POSITIVE LOGITS
     criminally
    1.40
     harshly
    1.05
     unjust
    1.00
     unfairly
    1.00
     unnecessarily
    0.91
     liable
    0.87
     accountable
    0.84
     complicit
    0.83
    soever
    0.82
     merciless
    0.82
    Activations Density 0.239%

    No Known Activations