© 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. 9285
    Prev
    Next
    INDEX
    Explanations

    bills or legislative actions

    oai_token-act-pair · gpt-3.5-turbo

    references to legislation or bills being discussed or proposed

    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
     Pv
    -0.71
     Flavoring
    -0.70
     Ashes
    -0.68
     Sul
    -0.67
    raction
    -0.67
     Virtue
    -0.66
     Distribution
    -0.65
     Canal
    -0.63
    vent
    -0.63
     Drift
    -0.63
    POSITIVE LOGITS
    iard
    1.29
    bill
    0.83
    BILL
    0.83
    owing
    0.81
     bill
    0.80
    ings
    0.79
    clinton
    0.79
     bills
    0.79
    inventoryQuantity
    0.77
    book
    0.77
    Activations Density 0.027%

    No Known Activations