© 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. 1-RES-JB
    11. 1934
    Prev
    Next
    INDEX
    Explanations

    phrases related to military ranks and positions, specifically 'Sgt'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the rank "Sgt" associated with military personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perm
    -0.73
    ahime
    -0.69
    phal
    -0.68
    fecture
    -0.65
    relations
    -0.63
    Dub
    -0.62
    hur
    -0.62
    âĶģ
    -0.61
    trak
    -0.60
    pour
    -0.60
    POSITIVE LOGITS
     Sgt
    1.44
    geant
    1.14
    gt
    1.03
     Sergeant
    1.01
     sergeant
    0.98
     Lt
    0.86
    cipled
    0.83
     Battalion
    0.74
     Trooper
    0.73
    veland
    0.73
    Activations Density 0.008%

    No Known Activations