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. 6160
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Russ"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or entities, particularly those associated with the name "Russ" or related variants

    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
    mable
    -0.71
    nce
    -0.71
    sections
    -0.70
    enment
    -0.65
    instance
    -0.64
     conspicuous
    -0.63
    DER
    -0.62
     td
    -0.61
    $$
    -0.61
    District
    -0.61
    POSITIVE LOGITS
     Russ
    0.92
    akov
    0.88
    achev
    0.88
    aldo
    0.86
    kies
    0.84
    anova
    0.84
    illo
    0.83
    ault
    0.83
    kaya
    0.80
    Russ
    0.80
    Activations Density 0.018%

    No Known Activations