© 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. 6-RES-JB
    11. 17829
    Prev
    Next
    INDEX
    Explanations

    legal terms and court-related actions

    oai_token-act-pair · gpt-3.5-turbo

    legal terms related to injunctions and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yles
    -0.76
    eem
    -0.75
     Folk
    -0.72
    ħĭ
    -0.72
    ndra
    -0.72
    gression
    -0.71
    rics
    -0.70
     McCann
    -0.68
    nder
    -0.66
    tz
    -0.66
    POSITIVE LOGITS
     restraining
    0.76
     injunction
    0.72
     opposed
    0.71
    ishment
    0.70
     wart
    0.69
    emate
    0.68
     battle
    0.67
    enged
    0.66
    wart
    0.65
     stoked
    0.65
    Activations Density 0.039%

    No Known Activations