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. 4741
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement or military units, particularly those named "Squad."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "squad" in various contexts

    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
    pport
    -0.79
    ocaust
    -0.77
    orgetown
    -0.72
    ocent
    -0.72
    éĽ
    -0.71
    utenberg
    -0.71
    iley
    -0.68
    gra
    -0.67
    pire
    -0.67
    Downloadha
    -0.65
    POSITIVE LOGITS
    rons
    1.83
    mates
    1.14
     mates
    0.97
    members
    0.94
     Leader
    0.88
    leader
    0.88
    mate
    0.85
    alid
    0.82
     members
    0.80
    aris
    0.80
    Activations Density 0.032%

    No Known Activations