© 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. 7-RES-JB
    11. 17223
    Prev
    Next
    INDEX
    Explanations

    phrases related to wars and battles

    oai_token-act-pair · gpt-3.5-turbo

    references to war-related titles and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.73
     Helpful
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
    ħĭ
    -0.68
    */(
    -0.67
    ©¶æ¥µ
    -0.67
    TOP
    -0.66
    itte
    -0.65
    Publisher
    -0.65
    ograp
    -0.64
    POSITIVE LOGITS
    enegger
    1.00
    schild
    0.82
     attrition
    0.81
    istan
    0.79
     Afghanistan
    0.79
     Armageddon
    0.77
     raged
    0.74
    adesh
    0.72
    torn
    0.69
     opium
    0.68
    Activations Density 0.207%

    No Known Activations