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. 3-RES-JB
    6. 21829
    Prev
    Next
    INDEX
    Explanations

    terms related to military organizations and operations, particularly focusing on the IDF (Israel Defense Forces)

    oai_token-act-pair · gpt-3.5-turbo

    references to military organizations and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luaj
    -0.81
     Fey
    -0.73
     Nig
    -0.70
     Prosper
    -0.70
     Rockefeller
    -0.69
     Humanity
    -0.69
    Machine
    -0.68
    itarian
    -0.67
    istic
    -0.64
    Dub
    -0.63
    POSITIVE LOGITS
     reserv
    0.88
    CCC
    0.86
    OSH
    0.83
     colonel
    0.82
    REP
    0.80
    KK
    0.79
    ESH
    0.78
    CHR
    0.77
    TA
    0.77
    VICE
    0.76
    Activations Density 0.014%

    No Known Activations