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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 695
    Prev
    Next
    INDEX
    Explanations

    terms related to being complacent

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health insurance and associated conditions

    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
    gd
    -0.81
    pb
    -0.69
    onian
    -0.68
     Kerr
    -0.67
    essential
    -0.66
    ranch
    -0.64
    Power
    -0.64
     friendships
    -0.64
    iton
    -0.64
    ronics
    -0.62
    POSITIVE LOGITS
    acent
    2.66
     uninsured
    1.87
     unaff
    1.62
    gged
    1.30
     trailed
    1.20
    imming
    1.20
     trailing
    1.17
     dubious
    1.11
     insured
    1.02
     unsur
    1.00
    Activations Density 0.026%

    No Known Activations