© 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. 12549
    Prev
    Next
    INDEX
    Explanations

    words related to the legal profession, particularly the term "lawyer."

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "lawyer."

    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
    ivia
    -0.69
    OPS
    -0.69
    اÙĦ
    -0.66
     gulf
    -0.64
    drawn
    -0.63
     heaviest
    -0.63
    ß
    -0.58
     runaway
    -0.58
    uncture
    -0.58
     decay
    -0.57
    POSITIVE LOGITS
    yer
    0.95
    chell
    0.88
    holm
    0.87
    stein
    0.85
    baum
    0.82
    ner
    0.80
    berg
    0.79
    horn
    0.78
    bats
    0.78
    rors
    0.75
    Activations Density 0.011%

    No Known Activations