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. 8-RES-JB
    6. 21586
    Prev
    Next
    INDEX
    Explanations

    countries and regions around the world

    oai_token-act-pair · gpt-3.5-turbo

    mentions of countries and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tops
    -0.72
    iple
    -0.67
     displeasure
    -0.61
     bargain
    -0.60
    sequence
    -0.60
    essen
    -0.60
    ebin
    -0.60
    notation
    -0.60
    vol
    -0.60
     deposition
    -0.58
    POSITIVE LOGITS
     Yard
    0.93
     Today
    0.83
     Airlines
    0.80
     Votes
    0.76
    borg
    0.76
    XT
    0.76
    ican
    0.75
     Reborn
    0.75
    ophobic
    0.74
    's
    0.73
    Activations Density 0.206%

    No Known Activations