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. 4404
    Prev
    Next
    INDEX
    Explanations

    references to governmental actions or policies, specifically related to budget cuts and legal decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to political actions or measures taken by Republican officials

    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
    hest
    -0.60
    asma
    -0.59
    oult
    -0.59
    tan
    -0.58
    utenberg
    -0.57
    XY
    -0.56
    Balance
    -0.54
    afort
    -0.54
     Liquid
    -0.54
    ractor
    -0.54
    POSITIVE LOGITS
     everywhere
    1.32
     nationwide
    1.23
     elsewhere
    1.23
     across
    1.22
     worldwide
    1.16
     Everywhere
    1.09
     throughout
    1.01
     globally
    1.01
    Across
    0.99
     Across
    0.96
    Activations Density 0.988%

    No Known Activations