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. 9-RES-JB
    6. 1262
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    names of countries, organizations, and institutions related to politics and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spir
    -0.58
    aeda
    -0.48
    enfranch
    -0.46
    schild
    -0.45
    profits
    -0.45
    imates
    -0.45
    uries
    -0.44
    ormon
    -0.44
     crowds
    -0.43
    stories
    -0.43
    POSITIVE LOGITS
    cellaneous
    0.50
    actionDate
    0.45
     ILCS
    0.45
    ĨĴ
    0.45
    VIDIA
    0.42
    Leod
    0.41
    externalActionCode
    0.41
    »Ĵ
    0.40
    unknown
    0.40
    itably
    0.40
    Activations Density 0.975%

    No Known Activations