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. 10-RES-JB
    6. 8857
    Prev
    Next
    INDEX
    Explanations

    countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries and their actions or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uces
    -0.79
    bum
    -0.68
     Kills
    -0.63
    getic
    -0.63
    grades
    -0.63
    Writ
    -0.63
    ipl
    -0.62
    Translation
    -0.62
    reads
    -0.62
    Lear
    -0.61
    POSITIVE LOGITS
     have
    1.32
     are
    1.29
     owe
    1.17
     intend
    1.13
     contend
    1.12
     rely
    1.12
     boast
    1.10
     refuse
    1.09
     operate
    1.08
     insist
    1.08
    Activations Density 0.331%

    No Known Activations