© 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. 21727
    Prev
    Next
    INDEX
    Explanations

    legal terms or actions related to lawsuits

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and phrases related to lawsuits and legal actions

    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
    ahime
    -0.81
    horn
    -0.79
    rika
    -0.77
    isSpecialOrderable
    -0.77
    agall
    -0.76
    plom
    -0.75
    peak
    -0.74
    merga
    -0.73
     mull
    -0.73
    vell
    -0.71
    POSITIVE LOGITS
     wrongful
    1.24
     negligent
    1.24
     neglig
    1.22
     Defendants
    1.21
     misrepresent
    1.20
     negligence
    1.17
     unlawfully
    1.14
     improperly
    1.11
     unfair
    1.07
     damages
    1.05
    Activations Density 0.363%

    No Known Activations