© 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. 4-RES-JB
    11. 10221
    Prev
    Next
    INDEX
    Explanations

    phrases related to wars

    oai_token-act-pair · gpt-3.5-turbo

    references to wars and conflicts

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

    No Comments

    Negative Logits
    obook
    -0.75
     kinderg
    -0.71
    ITIES
    -0.65
    ITY
    -0.64
     nonex
    -0.64
    pert
    -0.64
    Ħ¢
    -0.64
    Chance
    -0.63
    Magikarp
    -0.62
    random
    -0.60
    POSITIVE LOGITS
    lords
    1.07
    lord
    0.99
    fighting
    0.88
    riors
    0.84
     War
    0.84
    fare
    0.83
     Veterans
    0.82
    rior
    0.82
     Era
    0.81
     era
    0.80
    Activations Density 0.032%

    No Known Activations