© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 7052
    Prev
    Next
    INDEX
    Explanations

    technical terms related to weaponry

    oai_token-act-pair · gpt-3.5-turbo

    terms related to advanced weaponry and military equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leaks
    -0.77
    Disney
    -0.74
    Parents
    -0.73
     booking
    -0.73
    weet
    -0.73
     Cinderella
    -0.73
    mone
    -0.73
     booked
    -0.73
    soDeliveryDate
    -0.72
    çĶŁ
    -0.71
    POSITIVE LOGITS
     turret
    1.71
     cannons
    1.58
     cannon
    1.56
     infantry
    1.50
     turrets
    1.50
     artillery
    1.50
     grenade
    1.46
     Infantry
    1.40
     armour
    1.40
     grenades
    1.39
    Activations Density 0.223%

    No Known Activations