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. 24531
    Prev
    Next
    INDEX
    Explanations

    references to locations or organizations related to the British Virgin Islands

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Virgin" in various contexts

    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
     offensively
    -0.77
     addon
    -0.73
    np
    -0.73
     Shapiro
    -0.71
     defensively
    -0.68
    rha
    -0.67
    etooth
    -0.67
     melee
    -0.67
    ogy
    -0.66
     drafting
    -0.65
    POSITIVE LOGITS
     Virgin
    4.49
    Virgin
    3.61
     virgin
    2.19
    irgin
    1.96
     Virginia
    1.41
     virginity
    1.38
    Virginia
    1.32
     Madonna
    1.17
     Fairfax
    1.16
     McDonnell
    1.10
    Activations Density 0.024%

    No Known Activations