Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20687
    Prev
    Next
    INDEX
    Explanations

    venture capital related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to hedge-related financial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kub
    -0.76
    RAW
    -0.75
    VO
    -0.72
    Inv
    -0.68
     Korra
    -0.67
    XXX
    -0.66
    cohol
    -0.65
     Lima
    -0.65
     Vis
    -0.64
    raped
    -0.64
    POSITIVE LOGITS
     hedge
    4.01
     Hedge
    2.98
     hed
    2.33
    Wall
    1.02
     Hed
    0.97
     biotech
    0.97
     securities
    0.96
     derivatives
    0.95
     trader
    0.93
     banker
    0.92
    Activations Density 0.024%

    No Known Activations