© 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. 7117
    Prev
    Next
    INDEX
    Explanations

    information related to the ISIS organization, its fighters, and their activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ISIS and its 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
    uckland
    -1.02
     Pebble
    -0.84
     Garfield
    -0.81
     Chung
    -0.79
     Baseball
    -0.77
     Dickens
    -0.76
    robe
    -0.76
    Consumer
    -0.74
     Watergate
    -0.72
     Carpenter
    -0.72
    POSITIVE LOGITS
     ISIS
    2.29
     ISIL
    2.03
    ISIS
    2.02
     Raqqa
    2.01
     Baghd
    1.98
     Daesh
    1.92
     caliphate
    1.82
     jihadists
    1.82
     Mosul
    1.81
     jihadist
    1.77
    Activations Density 0.404%

    No Known Activations