© 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. 3-RES-JB
    11. 1704
    Prev
    Next
    INDEX
    Explanations

    references to events or entities related to the conflict in Iraq

    oai_token-act-pair · gpt-3.5-turbo

    references to Iraq and its people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verett
    -0.85
    ertodd
    -0.84
    eries
    -0.82
    alty
    -0.82
    aminer
    -0.81
    smanship
    -0.81
    ritch
    -0.80
    ilver
    -0.76
    */(
    -0.72
    clipse
    -0.72
    POSITIVE LOGITS
     Kurdistan
    1.21
     Hussein
    0.98
     Iraqi
    0.98
     Iraqis
    0.90
     insurgents
    0.89
     Kurds
    0.88
    Iraq
    0.87
     dictator
    0.87
     Arab
    0.85
     fatig
    0.84
    Activations Density 0.006%

    No Known Activations