© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10440
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Hill" followed by a number or description

    oai_token-act-pair · gpt-3.5-turbo

    references to "The Hill," a political news website and publication

    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
    âĹ¼
    -0.83
    ============
    -0.71
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
    cial
    -0.68
    ========
    -0.67
    Slot
    -0.67
    Export
    -0.65
     Emir
    -0.64
    Wan
    -0.64
     Marketable
    -0.64
    POSITIVE LOGITS
    iard
    1.12
     Hill
    1.06
    stones
    0.92
    side
    0.92
    dale
    0.88
    boro
    0.87
    castle
    0.87
    hill
    0.85
    mont
    0.83
    stone
    0.83
    Activations Density 0.011%

    No Known Activations