© 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. 4-RES-JB
    11. 4233
    Prev
    Next
    INDEX
    Explanations

    terms related to financial investments or business dealings involving large sums of money

    oai_token-act-pair · gpt-3.5-turbo

    words associated with planning and strategy

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

    No Comments

    Negative Logits
    PRES
    -0.83
    âĸ¬
    -0.83
    VICE
    -0.79
    âĸ¬âĸ¬
    -0.76
    SPONSORED
    -0.73
     Governors
    -0.72
     Masters
    -0.71
    FINE
    -0.71
    Interstitial
    -0.71
    FINEST
    -0.70
    POSITIVE LOGITS
    ump
    1.14
    umber
    1.11
    atter
    1.09
    umm
    1.09
    aques
    1.07
    ipp
    1.07
    umbers
    1.04
    umb
    1.04
    ucked
    1.04
    anted
    1.03
    Activations Density 0.008%

    No Known Activations