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. 3-RES-JB
    6. 2125
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Vic" along with related words or variations like "vicarious" and "Vicente."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Vic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.87
    xual
    -0.81
    landish
    -0.80
    dress
    -0.77
    tenance
    -0.76
     EntityItem
    -0.75
    pread
    -0.74
    Ô
    -0.74
    pmwiki
    -0.71
    manship
    -0.71
    POSITIVE LOGITS
    arious
    1.18
    inity
    1.08
    entric
    1.03
    isions
    0.97
     Vic
    0.95
    ision
    0.91
    iple
    0.91
    ente
    0.90
    uous
    0.88
    imates
    0.87
    Activations Density 0.007%

    No Known Activations