© 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. 2-RES-JB
    11. 11279
    Prev
    Next
    INDEX
    Explanations

    words related to a specific political and religious figure, Ayatollah Ali Khamenei

    oai_token-act-pair · gpt-3.5-turbo

    references to specific political leaders or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scot
    -0.87
     Hurricanes
    -0.84
     Oregon
    -0.83
     Vikings
    -0.83
     Wilmington
    -0.81
     Viking
    -0.79
     Oaks
    -0.77
     Isles
    -0.77
     Hawth
    -0.75
     Sussex
    -0.74
    POSITIVE LOGITS
    enei
    1.88
     Kham
    1.28
    ollah
    1.23
    idium
    0.94
    ategory
    0.93
    oÄŁan
    0.91
    aganda
    0.91
    isen
    0.91
    ishi
    0.91
    osate
    0.91
    Activations Density 0.013%

    No Known Activations