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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 20643
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal language

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "language" and its context, especially related to legislation and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roxy
    -0.85
    ECD
    -0.80
    ilon
    -0.80
    minster
    -0.79
    ilts
    -0.78
    rodu
    -0.75
    rium
    -0.73
    kus
    -0.72
    rd
    -0.71
     Ended
    -0.71
    POSITIVE LOGITS
     learners
    0.94
     language
    0.91
     spoken
    0.90
    anguage
    0.90
     interpreter
    0.88
     immersion
    0.86
    language
    0.85
     barrier
    0.84
     barriers
    0.83
     insensitive
    0.81
    Activations Density 0.014%

    No Known Activations