Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13746
    Prev
    Next
    INDEX
    Explanations

    mentions of the American people

    oai_token-act-pair · gpt-3.5-turbo

    references to the "American people."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.84
    catentry
    -0.84
    Smith
    -0.70
    Prev
    -0.69
    TAG
    -0.69
    à¸
    -0.67
    Reloaded
    -0.65
     promotional
    -0.65
    SET
    -0.64
    tein
    -0.64
    POSITIVE LOGITS
    folk
    0.83
    ocracy
    0.80
    hood
    0.78
     electing
    0.75
     uprising
    0.75
     elected
    0.72
    orate
    0.72
     harmed
    0.68
     entrusted
    0.68
    orsi
    0.67
    Activations Density 0.043%

    No Known Activations