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. 4-RES-JB
    6. 8397
    Prev
    Next
    INDEX
    Explanations

    references to military ranks and figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of military ranks, specifically "Colonel."

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

    No Comments

    Negative Logits
     Pengu
    -0.75
    sett
    -0.73
    lins
    -0.72
    irlf
    -0.70
    itar
    -0.69
    thora
    -0.69
    elf
    -0.68
    robat
    -0.66
     Chaser
    -0.64
    pun
    -0.64
    POSITIVE LOGITS
     Gaddafi
    0.86
    LECT
    0.85
    onel
    0.82
    terday
    0.75
    ĸļ
    0.75
    xual
    0.74
    agne
    0.72
    ktop
    0.70
    ength
    0.69
    trl
    0.68
    Activations Density 0.045%

    No Known Activations