© 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. 12583
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or individuals, particularly the name "Hague."

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and places related to political events

    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
    idity
    -0.91
    orescent
    -0.72
    istors
    -0.71
    forms
    -0.70
    uder
    -0.70
    isle
    -0.69
    icides
    -0.68
    idation
    -0.68
     cooks
    -0.67
    udeau
    -0.67
    POSITIVE LOGITS
    vernment
    0.83
     Lans
    0.81
    ç·
    0.73
    emouth
    0.71
    cloth
    0.70
    RAFT
    0.66
     Herz
    0.65
    etz
    0.65
    enegger
    0.65
    HL
    0.64
    Activations Density 0.023%

    No Known Activations