© 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. 11-RES-JB
    11. 18734
    Prev
    Next
    INDEX
    Explanations

    phrases related to terrorism and extremist groups

    oai_token-act-pair · gpt-3.5-turbo

    terms related to terrorist organizations and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hetti
    -0.87
    uci
    -0.83
     Supervisor
    -0.74
    åħī
    -0.73
     Baseball
    -0.73
    LECT
    -0.73
     Prix
    -0.73
     Pebble
    -0.72
     Marlins
    -0.72
     Phillies
    -0.71
    POSITIVE LOGITS
     strongh
    1.29
     caliphate
    1.24
     insurgency
    1.20
     Baghd
    1.13
     stronghold
    1.11
     militants
    1.11
     affiliates
    1.10
     recruitment
    1.09
    iphate
    1.08
     fighters
    1.07
    Activations Density 0.288%

    No Known Activations