© 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. 2-RES-JB
    11. 9098
    Prev
    Next
    INDEX
    Explanations

    phrases related to military units or specific commands

    oai_token-act-pair · gpt-3.5-turbo

    references to military commands or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OHN
    -0.69
     Niet
    -0.69
     Democr
    -0.65
     soluble
    -0.64
     Schne
    -0.60
     Anita
    -0.60
    aunder
    -0.58
     Rhod
    -0.58
     Shapiro
    -0.57
     heterogeneity
    -0.57
    POSITIVE LOGITS
    eering
    1.13
     Command
    1.06
    eers
    0.99
    eer
    0.96
     Commands
    0.90
    Command
    0.89
    eur
    0.87
    force
    0.85
    hammer
    0.84
    quartered
    0.83
    Activations Density 0.008%

    No Known Activations