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. 1-RES-JB
    6. 11913
    Prev
    Next
    INDEX
    Explanations

    the name "Vic" or variations of it within sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or entity named "Vic."

    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
    tenance
    -0.83
    */(
    -0.82
    dress
    -0.79
    pread
    -0.78
    pmwiki
    -0.77
    Poké
    -0.76
    eting
    -0.73
    landish
    -0.73
    xual
    -0.72
    SpaceEngineers
    -0.71
    POSITIVE LOGITS
     Vic
    1.15
    arious
    1.03
    entric
    0.96
     vic
    0.95
    inity
    0.94
    isions
    0.91
    ocese
    0.86
    uous
    0.86
    abulary
    0.85
    ente
    0.84
    Activations Density 0.003%

    No Known Activations