© 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. 11-RES-JB
    11. 150
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws, regulations, and requirements

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with roles, responsibilities, and legal requirements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    whel
    -0.68
     enthus
    -0.65
     lately
    -0.62
    oward
    -0.62
    ensical
    -0.61
     newcom
    -0.61
     mathemat
    -0.59
     dstg
    -0.58
    flix
    -0.58
    ORGE
    -0.57
    POSITIVE LOGITS
     must
    1.62
    must
    1.47
     cannot
    1.46
     MUST
    1.36
    shall
    1.33
     SHALL
    1.22
     can
    1.20
     shall
    1.12
     forfeit
    1.10
     SHOULD
    1.08
    Activations Density 0.302%

    No Known Activations