© 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. 0-RES-JB
    11. 4309
    Prev
    Next
    INDEX
    Explanations

    phrases related to military and armed forces

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pear
    -0.68
     pearl
    -0.67
     deficient
    -0.64
    YR
    -0.62
    by
    -0.61
     cheaply
    -0.60
     cooler
    -0.60
    ox
    -0.60
     reinvest
    -0.59
     booking
    -0.59
    POSITIVE LOGITS
     Forces
    4.07
     forces
    2.19
     Force
    2.01
    forces
    1.88
    Force
    1.60
    force
    1.47
     force
    1.36
     Corps
    1.32
     Armed
    1.25
     Causes
    1.19
    Activations Density 0.009%

    No Known Activations