© 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. 2-RES-JB
    11. 19481
    Prev
    Next
    INDEX
    Explanations

    legal terms and procedures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal proceedings or formal declarations

    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
     gigs
    -0.87
     highs
    -0.79
    Jet
    -0.78
    worms
    -0.77
     laughs
    -0.76
     Slim
    -0.73
     hugs
    -0.73
     Glow
    -0.72
     lows
    -0.68
    scenes
    -0.67
    POSITIVE LOGITS
     applicable
    1.09
     lawful
    1.03
     Applicant
    1.00
     lawfully
    0.97
    Applic
    0.95
     adjud
    0.95
     unlawful
    0.95
     Plaintiff
    0.93
     affirmative
    0.93
     appellant
    0.92
    Activations Density 2.952%

    No Known Activations