© 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. 3-RES-JB
    11. 11409
    Prev
    Next
    INDEX
    Explanations

    words related to financial terms or numbers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial or business contexts, particularly involving bankruptcy and disruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omething
    -0.69
     Havana
    -0.65
     Monarch
    -0.64
     reconc
    -0.63
     Franco
    -0.62
     thirds
    -0.62
     Shades
    -0.61
     Highlander
    -0.60
     Caldwell
    -0.60
     SOS
    -0.60
    POSITIVE LOGITS
    ulously
    1.09
    oulos
    1.04
    phrine
    0.99
    culation
    0.94
    artisan
    0.94
    odcast
    0.93
    pees
    0.92
    igon
    0.89
    ole
    0.87
    inion
    0.85
    Activations Density 0.014%

    No Known Activations