© 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. 1-RES-JB
    11. 14358
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific legal or regulatory provisions

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative or regulatory provisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psy
    -0.80
    pper
    -0.70
    cer
    -0.68
    ritz
    -0.65
    arton
    -0.64
    aminer
    -0.63
    oca
    -0.63
    raid
    -0.61
     brow
    -0.60
     Gall
    -0.60
    POSITIVE LOGITS
     provisions
    1.05
    witz
    0.84
    afety
    0.80
    MENTS
    0.79
     stip
    0.77
    ãĥ¼ãĥĨãĤ£
    0.77
    ĸļ
    0.76
    iveness
    0.73
    manship
    0.72
    ttes
    0.70
    Activations Density 0.004%

    No Known Activations