© 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. 10467
    Prev
    Next
    INDEX
    Explanations

    phrases related to military and armed forces

    oai_token-act-pair · gpt-3.5-turbo

    references to the acronym "AF"

    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
     Meier
    -0.83
     measure
    -0.73
     Xu
    -0.66
     wholesale
    -0.63
     Incarnation
    -0.62
     Reck
    -0.62
     Lara
    -0.62
     racket
    -0.61
     Dmitry
    -0.60
     monopoly
    -0.60
    POSITIVE LOGITS
    AF
    4.30
     AF
    1.94
    AAF
    1.78
    af
    1.74
    AE
    1.62
    EF
    1.44
    CF
    1.40
    IF
    1.40
    Af
    1.37
    BF
    1.36
    Activations Density 0.010%

    No Known Activations