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. 21263
    Prev
    Next
    INDEX
    Explanations

    notable names or terms related to various industries or fields

    oai_token-act-pair · gpt-3.5-turbo

    names of people involved in the arts and entertainment industry

    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
    burning
    -0.75
     degrading
    -0.70
    negative
    -0.70
     sting
    -0.69
    threatening
    -0.69
    Republican
    -0.69
    soType
    -0.68
    acists
    -0.68
    ndum
    -0.67
    fail
    -0.67
    POSITIVE LOGITS
     collaborated
    1.19
     teamed
    1.16
     explains
    1.07
     oversees
    1.07
     pioneered
    1.05
     specializes
    1.05
     introduces
    1.04
     collabor
    1.04
     coined
    1.03
     curated
    1.02
    Activations Density 0.591%

    No Known Activations