© 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. 7-RES-JB
    11. 3931
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Syrian government and related geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inarily
    -0.92
    WARD
    -0.86
    owler
    -0.80
    otle
    -0.79
    print
    -0.78
    uckland
    -0.78
    é¾įå
    -0.76
    ocobo
    -0.76
    hem
    -0.76
    ertodd
    -0.74
    POSITIVE LOGITS
     Arab
    1.08
     refugee
    0.98
     refugees
    0.97
     Refugees
    0.97
     Kurds
    0.93
     Assad
    0.92
    Assad
    0.92
     Syrians
    0.87
     Syrian
    0.86
     Aleppo
    0.84
    Activations Density 0.034%

    No Known Activations