© 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. 10-RES-JB
    11. 16312
    Prev
    Next
    INDEX
    Explanations

    phrases related to different aspects of war or conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to "war on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rete
    -0.79
    OGR
    -0.79
    HF
    -0.76
    wcs
    -0.76
    rawdownloadcloneembedreportprint
    -0.75
    alore
    -0.74
    natureconservancy
    -0.74
    ulic
    -0.73
    UF
    -0.70
    ittal
    -0.70
    POSITIVE LOGITS
     drugs
    1.06
     terror
    1.03
     terrorism
    0.97
     Drugs
    0.94
     Terror
    0.92
    terror
    0.90
     Poverty
    0.85
     poverty
    0.84
     whistleblowers
    0.80
     Terrorism
    0.78
    Activations Density 0.079%

    No Known Activations