© 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 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. 4657
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and governmental processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government, legal, and institutional contexts

    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
    ombs
    -0.61
    amaz
    -0.61
    apeake
    -0.60
     Flavoring
    -0.59
    quished
    -0.59
     Vengeance
    -0.58
     newfound
    -0.56
    undai
    -0.56
    reci
    -0.56
    ukong
    -0.54
    POSITIVE LOGITS
     rather
    1.40
     anyways
    1.30
     whereas
    1.25
     anyway
    1.21
    rather
    1.09
     instead
    0.95
     unlike
    0.91
     regardless
    0.88
     ONLY
    0.85
     irrespective
    0.82
    Activations Density 0.798%

    No Known Activations