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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4742
    Prev
    Next
    INDEX
    Explanations

    mentions of the "American Kennel Club"

    oai_token-act-pair · gpt-3.5-turbo

    references to the American Kennel Club and its activities

    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
    TABLE
    -0.64
    table
    -0.62
     nerv
    -0.62
     morbid
    -0.61
     Revelations
    -0.60
    senal
    -0.59
    DIT
    -0.59
     Uzbek
    -0.59
     Fas
    -0.58
     rainy
    -0.58
    POSITIVE LOGITS
    Kenn
    1.29
     Kenn
    1.21
    edy
    0.97
    ety
    0.94
    emouth
    0.87
    ett
    0.86
    iken
    0.86
    ahan
    0.84
    eteen
    0.84
    eto
    0.83
    Activations Density 0.008%

    No Known Activations