© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18329
    Prev
    Next
    INDEX
    Explanations

    various forms of the word 'enforced'

    oai_token-act-pair · gpt-3.5-turbo

    references to rules or regulations being put into effect

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nuts
    -0.75
    nut
    -0.69
     Shares
    -0.69
    icio
    -0.68
    Maker
    -0.67
    stocks
    -0.64
    DK
    -0.64
    tal
    -0.63
    crop
    -0.63
    umps
    -0.63
    POSITIVE LOGITS
     enforced
    3.56
    forced
    1.38
     enforcing
    1.35
     imposed
    1.35
     polic
    1.31
     upheld
    1.18
     outlawed
    1.16
     tolerated
    1.14
     Forced
    1.10
     overturned
    1.07
    Activations Density 0.025%

    No Known Activations