© 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. 11844
    Prev
    Next
    INDEX
    Explanations

    mentions of military terms related to weapons and attacks like "mortar," "rocket," "artillery," and "shelling."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military action and artillery-related activities

    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
     Indigo
    -0.91
    spir
    -0.86
    âĶĢâĶĢâĶĢâĶĢ
    -0.85
    Redd
    -0.82
    Scot
    -0.81
    Vert
    -0.80
     Revel
    -0.79
    natureconservancy
    -0.77
    Stew
    -0.75
    çĶ°
    -0.75
    POSITIVE LOGITS
     shelling
    1.24
     barr
    1.23
     bombardment
    1.20
     artillery
    1.17
     bombard
    1.13
     grenades
    1.06
     bombed
    1.03
     penetrating
    1.01
     bombing
    0.99
     detonated
    0.98
    Activations Density 0.115%

    No Known Activations