© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20782
    Prev
    Next
    INDEX
    Explanations

    phrases related to terrorism

    oai_token-act-pair · gpt-3.5-turbo

    references to terror-related events or groups

    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
    bye
    -0.69
    resso
    -0.68
     Quartz
    -0.66
    galitarian
    -0.64
    rovers
    -0.63
    Ģ
    -0.63
    flush
    -0.63
    Salt
    -0.63
    lease
    -0.61
     Rhod
    -0.59
    POSITIVE LOGITS
    istic
    1.04
    izing
    1.04
    fully
    1.02
    ization
    0.95
    ising
    0.88
    fulness
    0.87
    ophobic
    0.87
    ously
    0.87
    otropic
    0.87
    icious
    0.86
    Activations Density 0.020%

    No Known Activations