© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4681
    Prev
    Next
    INDEX
    Explanations

    legal terms and proceedings, with a focus on objections, decisions, and defenses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to legal arguments and defenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.69
     Skydragon
    -0.64
     Collider
    -0.64
     adolesc
    -0.63
    circle
    -0.62
    region
    -0.61
    Cod
    -0.59
    owship
    -0.59
    ׾
    -0.58
    oother
    -0.57
    POSITIVE LOGITS
     argument
    1.52
     arguments
    1.51
     case
    1.31
     objections
    1.30
     objection
    1.24
     contention
    1.23
    argument
    1.17
     claim
    1.11
     Argument
    1.08
     appeal
    1.07
    Activations Density 0.524%

    No Known Activations