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. 14544
    Prev
    Next
    INDEX
    Explanations

    names of persons related to political or expert positions

    oai_token-act-pair · gpt-3.5-turbo

    the presence of proper nouns, particularly names and titles

    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
    Decre
    -0.68
    rums
    -0.68
     ital
    -0.62
    aceae
    -0.62
    lly
    -0.61
    planes
    -0.60
    IUM
    -0.59
    iren
    -0.58
    process
    -0.58
    cept
    -0.58
    POSITIVE LOGITS
     director
    1.13
     chairman
    1.12
     superintendent
    1.05
     dean
    1.04
     spokesman
    1.03
     vice
    1.03
     president
    1.03
     founder
    1.01
     Director
    0.98
     chief
    0.98
    Activations Density 0.130%

    No Known Activations