© 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. 9-RES-JB
    11. 4324
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms and financial transactions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -,
    -0.76
    ulously
    -0.63
    ®,
    -0.62
     willfully
    -0.59
     marvelous
    -0.58
     godd
    -0.58
     goofy
    -0.57
     goddamn
    -0.56
    +,
    -0.56
    illions
    -0.55
    POSITIVE LOGITS
     tyres
    0.71
     tyre
    0.66
    avour
    0.65
    '."
    0.61
    `.
    0.61
    hra
    0.61
     neighbours
    0.60
     rall
    0.59
    ".
    0.58
    etheless
    0.58
    Activations Density 1.736%

    No Known Activations