© 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. 3-RES-JB
    11. 4372
    Prev
    Next
    INDEX
    Explanations

    words related to legal or procedural matters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal proceedings and formal events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.54
    rogens
    -0.50
     Scenes
    -0.49
     Vehicles
    -0.45
    urches
    -0.45
    tics
    -0.45
    eworks
    -0.45
    rencies
    -0.43
    atography
    -0.43
    hops
    -0.43
    POSITIVE LOGITS
     lesson
    0.51
     motive
    0.48
     element
    0.47
     semblance
    0.46
     standpoint
    0.45
    uci
    0.45
     pattern
    0.45
     obligation
    0.45
     basis
    0.44
     arrangement
    0.44
    Activations Density 1.433%

    No Known Activations