© 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. 3067
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agreements

    oai_token-act-pair · gpt-3.5-turbo

    the word "in" as well as variations or phrases that include it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    âĿ
    -0.70
    ILLE
    -0.66
    76561
    -0.65
    REL
    -0.63
    resh
    -0.61
     savior
    -0.58
    yles
    -0.57
    Ľ
    -0.55
     nailed
    -0.54
    Capture
    -0.54
    POSITIVE LOGITS
     fact
    1.21
     spite
    1.20
    clud
    1.20
     addition
    1.15
     contrast
    1.12
    cluding
    1.12
     accordance
    1.10
    cluded
    1.08
    sect
    1.08
    clus
    1.03
    Activations Density 0.094%

    No Known Activations