© 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. 6-RES-JB
    11. 2896
    Prev
    Next
    INDEX
    Explanations

    phrases related to armed conflicts or militant groups

    oai_token-act-pair · gpt-3.5-turbo

    words related to guerrilla warfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hower
    -0.87
    ŃĶ
    -0.75
    picture
    -0.69
     Pradesh
    -0.68
     Redux
    -0.67
    quartered
    -0.66
     Cycle
    -0.64
    croft
    -0.64
     Spectrum
    -0.63
    20439
    -0.63
    POSITIVE LOGITS
    inea
    1.22
    vernment
    1.12
    cci
    1.00
    ilt
    1.00
    arding
    0.99
    ilts
    0.98
    ppy
    0.94
    aret
    0.88
    ile
    0.88
    arded
    0.86
    Activations Density 0.009%

    No Known Activations