© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22249
    Prev
    Next
    INDEX
    Explanations

    words related to military operations and strategy

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, titles, or concepts associated with intelligence and secrecy

    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
    HM
    -0.77
    ower
    -0.76
    ulton
    -0.75
    stru
    -0.74
    user
    -0.74
    udeb
    -0.71
    alogue
    -0.71
    regn
    -0.70
    rylic
    -0.69
    USER
    -0.69
    POSITIVE LOGITS
    atility
    0.85
     Gork
    0.81
     Emanuel
    0.72
     Emin
    0.70
    icated
    0.68
    giving
    0.67
     mole
    0.67
    reon
    0.66
    llah
    0.65
    andr
    0.64
    Activations Density 0.020%

    No Known Activations