© 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. 18500
    Prev
    Next
    INDEX
    Explanations

    numbers related to human casualties or population movements

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to casualties and displacements in conflict situations

    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
    inventoryQuantity
    -0.75
    hetics
    -0.73
     srfAttach
    -0.72
    quickShipAvailable
    -0.70
     superiors
    -0.70
     Excellence
    -0.66
    OLOG
    -0.64
     manag
    -0.64
     nicely
    -0.63
    ãĤ¦ãĤ¹
    -0.63
    POSITIVE LOGITS
     perished
    1.35
     died
    1.06
     starve
    1.05
     die
    1.01
     perish
    1.00
     starved
    0.96
     illegally
    0.95
     suffer
    0.95
     murdered
    0.92
     enrolled
    0.90
    Activations Density 0.331%

    No Known Activations