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. 7-RES-JB
    6. 1108
    Prev
    Next
    INDEX
    Explanations

    proper names or terms containing the syllable "gen."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, particularly by the name "Evgen" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eneg
    -0.75
    *=-
    -0.74
    aneers
    -0.69
    ModLoader
    -0.63
     disemb
    -0.62
     fri
    -0.61
    letal
    -0.60
     tradem
    -0.59
    mercial
    -0.59
     aph
    -0.59
    POSITIVE LOGITS
    ocide
    1.36
    esis
    1.34
    furt
    1.12
    uine
    1.11
    hardt
    1.04
    iuses
    1.00
    ius
    0.91
    holm
    0.88
    heimer
    0.88
    osc
    0.87
    Activations Density 0.020%

    No Known Activations