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. 3-RES-JB
    6. 10113
    Prev
    Next
    INDEX
    Explanations

    names ending in "ovic"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ovic," indicating names associated with specific cultural or ethnic backgrounds

    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
    reads
    -0.69
     WRITE
    -0.63
     fictitious
    -0.63
    Brave
    -0.62
     ACTIONS
    -0.61
     lofty
    -0.60
    LESS
    -0.59
     Hath
    -0.58
     Romantic
    -0.57
     youthful
    -0.56
    POSITIVE LOGITS
    ovic
    1.41
    vic
    1.01
    chini
    0.97
    icer
    0.96
    Äį
    0.94
    chio
    0.93
    chuk
    0.92
    ovich
    0.89
    Äĩ
    0.87
    ski
    0.84
    Activations Density 0.005%

    No Known Activations