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. 4-RES-JB
    6. 8901
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to Monaco

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and historical figures associated with Monaco and Napoleon

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

    No Comments

    Negative Logits
    aneers
    -0.93
    mable
    -0.80
    owship
    -0.79
    aya
    -0.75
    attery
    -0.75
    iffe
    -0.73
    ipt
    -0.72
    ore
    -0.69
    reen
    -0.69
    ittered
    -0.69
    POSITIVE LOGITS
     gland
    0.86
    cles
    0.75
    xiety
    0.74
    spective
    0.72
    arnaev
    0.70
     prostate
    0.70
    htaking
    0.68
    culosis
    0.68
    ificent
    0.67
    spection
    0.66
    Activations Density 0.023%

    No Known Activations