© 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. 593
    Prev
    Next
    INDEX
    Explanations

    locations and actions related to military operations against a specific extremist group

    oai_token-act-pair · gpt-3.5-turbo

    references to the Boko Haram group and related conflicts

    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
    Miller
    -0.93
    Ros
    -0.93
    Hamilton
    -0.89
    Denver
    -0.88
     Rosenthal
    -0.87
    Ross
    -0.86
    Pitt
    -0.86
    sburgh
    -0.85
     Rossi
    -0.82
     Stanton
    -0.79
    POSITIVE LOGITS
     Boko
    2.14
     Nigeria
    2.07
     Nigerian
    2.02
     Niger
    1.96
     Cameroon
    1.84
     Somalia
    1.72
     Kenya
    1.68
     Kenyan
    1.56
     Somali
    1.53
     Mali
    1.52
    Activations Density 0.165%

    No Known Activations