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. 6018
    Prev
    Next
    INDEX
    Explanations

    names ending with "ovic"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the surname "ovic"

    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
     utmost
    -0.63
    Brave
    -0.60
     course
    -0.59
     Breaking
    -0.59
     gist
    -0.59
     bumper
    -0.58
     fetus
    -0.57
     coarse
    -0.56
     eminent
    -0.56
     WRITE
    -0.55
    POSITIVE LOGITS
    ovic
    1.65
    vic
    1.09
    Äį
    0.99
    ovich
    0.96
    Äĩ
    0.95
    ovi
    0.93
    chini
    0.92
    chio
    0.91
    chuk
    0.91
    otti
    0.89
    Activations Density 0.006%

    No Known Activations