© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15630
    Prev
    Next
    INDEX
    Explanations

    points related to terms and conditions, restrictions, regulations, and legal language

    oai_token-act-pair · gpt-3.5-turbo

    structured punctuation and specific formatting in legal or formal documents

    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
    veland
    -0.69
    eki
    -0.64
    stown
    -0.63
     Turns
    -0.60
     dudes
    -0.60
    é¾
    -0.59
     stuff
    -0.58
     kids
    -0.58
    amy
    -0.57
    killer
    -0.57
    POSITIVE LOGITS
     namely
    1.44
     including
    1.42
     irrespective
    1.30
     thereby
    1.17
    including
    1.15
     regardless
    1.15
     respectively
    1.14
     includ
    1.11
     Including
    1.10
     pursuant
    1.09
    Activations Density 0.380%

    No Known Activations