© 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. 14619
    Prev
    Next
    INDEX
    Explanations

    legal terms and restrictions within a text

    oai_token-act-pair · gpt-3.5-turbo

    clauses related to unauthorized actions or connections

    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
    rils
    -0.71
    endor
    -0.71
    ideshow
    -0.67
    raved
    -0.66
     crunch
    -0.65
    usra
    -0.63
    rose
    -0.63
     Roose
    -0.62
    nell
    -0.62
    upiter
    -0.62
    POSITIVE LOGITS
     respectively
    1.16
     etc
    1.15
     thereby
    1.02
     pursuant
    1.01
     preferably
    1.01
     including
    1.00
     namely
    0.99
     INCLUD
    0.99
     regardless
    0.95
     except
    0.95
    Activations Density 0.468%

    No Known Activations