Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21349
    Prev
    Next
    INDEX
    Explanations

    mentions of war-related terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to "war" in various contexts

    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
    FORMATION
    -0.88
    Ħ¢
    -0.83
    essee
    -0.82
    aminer
    -0.74
    sembly
    -0.74
    ostics
    -0.73
    AUT
    -0.70
    Asset
    -0.70
    prints
    -0.69
    Distance
    -0.68
    POSITIVE LOGITS
    fare
    1.21
    lords
    1.14
    riors
    1.10
    lord
    1.08
    rior
    1.07
     waged
    0.96
    fighting
    0.96
    ring
    0.94
    fighter
    0.90
    fighters
    0.82
    Activations Density 0.030%

    No Known Activations