© 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. 9-RES-JB
    11. 3579
    Prev
    Next
    INDEX
    Explanations

    mentions related to attacks on the United States and its interests

    oai_token-act-pair · gpt-3.5-turbo

    references to terrorist threats and attacks against the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaru
    -0.78
    oult
    -0.75
    lopp
    -0.74
    olkien
    -0.73
    ISTORY
    -0.70
    ritis
    -0.68
    Adapter
    -0.64
     juggling
    -0.64
    chuk
    -0.63
     divergence
    -0.63
    POSITIVE LOGITS
     targets
    1.11
     civilians
    0.88
     throats
    0.87
     unarmed
    0.86
     premises
    0.85
     campuses
    0.84
     websites
    0.83
     beaches
    0.82
     homeland
    0.82
     innocent
    0.82
    Activations Density 0.477%

    No Known Activations