© 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. 10731
    Prev
    Next
    INDEX
    Explanations

    the word "Gaza" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Gaza

    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
    eanor
    -0.74
    lihood
    -0.71
    nant
    -0.71
     explan
    -0.71
    itivity
    -0.70
    Lear
    -0.69
    ATURE
    -0.67
     Scotch
    -0.67
    enegger
    -0.67
    pron
    -0.67
    POSITIVE LOGITS
     Strip
    1.18
     Gaza
    0.94
    Gaza
    0.84
     Lumpur
    0.80
     Hamas
    0.77
    abad
    0.77
     ravaged
    0.77
     Territories
    0.75
     devastated
    0.73
    lehem
    0.71
    Activations Density 0.008%

    No Known Activations