Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17240
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Tuzla"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Uz" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Siren
    -0.80
    ADS
    -0.70
    brates
    -0.68
    IFF
    -0.66
     Yards
    -0.63
     Predator
    -0.63
     Clicker
    -0.61
     Slater
    -0.60
     plaque
    -0.60
     Wooden
    -0.60
    POSITIVE LOGITS
    hao
    1.05
    uz
    1.01
    hou
    1.00
    awa
    0.90
    ombie
    0.87
    insk
    0.87
    daq
    0.83
    arah
    0.83
    alez
    0.82
    unda
    0.82
    Activations Density 0.011%

    No Known Activations