© 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. 5510
    Prev
    Next
    INDEX
    Explanations

    actions related to decision making or cancellation

    oai_token-act-pair · gpt-3.5-turbo

    words associated with legislative actions regarding approvals and denials

    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
    ingham
    -0.75
    agent
    -0.74
    izes
    -0.72
    abet
    -0.72
    ivities
    -0.71
    eners
    -0.71
    alter
    -0.70
    strength
    -0.68
    itis
    -0.68
    arist
    -0.68
    POSITIVE LOGITS
    uled
    0.94
     aback
    0.89
    ĸļ
    0.87
    CLASSIFIED
    0.85
     unanimously
    0.80
    ©¶æ¥µ
    0.77
    ocument
    0.76
     exting
    0.75
    nesday
    0.73
    DeliveryDate
    0.71
    Activations Density 0.075%

    No Known Activations