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. 8-RES-JB
    6. 17330
    Prev
    Next
    INDEX
    Explanations

    instances of theft or stealing activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating theft or being taken from a place or person

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ratulations
    -0.86
    merce
    -0.84
    ICA
    -0.76
    retty
    -0.76
    SPONSORED
    -0.72
    NEWS
    -0.71
    video
    -0.70
    interstitial
    -0.70
    meric
    -0.68
    phase
    -0.68
    POSITIVE LOGITS
     whence
    0.91
     unsuspecting
    0.88
     Palest
    0.87
     afar
    0.86
     thence
    0.80
     beneath
    0.80
     underneath
    0.80
     circulation
    0.78
     shelves
    0.73
     abroad
    0.71
    Activations Density 0.129%

    No Known Activations