Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 15500
    Prev
    Next
    INDEX
    Explanations

    words related to obedience and disobedience

    oai_token-act-pair · gpt-3.5-turbo

    terms related to obedience and compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spores
    -0.74
     Fargo
    -0.73
     Canadians
    -0.71
     VAT
    -0.69
    ofi
    -0.68
    andals
    -0.68
     Winnipeg
    -0.67
     KDE
    -0.66
     Helsinki
    -0.65
     pockets
    -0.65
    POSITIVE LOGITS
    edient
    1.32
     obedience
    1.27
     obe
    1.20
    edience
    1.15
     obedient
    1.12
     obey
    1.08
     disob
    1.04
    fulness
    1.04
    ĪĴ
    0.93
     heed
    0.87
    Activations Density 0.018%

    No Known Activations