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. 9-RES-JB
    6. 13026
    Prev
    Next
    INDEX
    Explanations

    financial and business-related terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with economic concepts and business dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Facebook
    -0.82
     Journalism
    -0.82
    YouTube
    -0.73
    ĸļ
    -0.71
    mosp
    -0.70
    nsics
    -0.69
    football
    -0.67
    eyes
    -0.67
    basketball
    -0.66
    Twitter
    -0.66
    POSITIVE LOGITS
     subsequent
    1.05
     intermediate
    0.92
     downstream
    0.89
     corresponding
    0.87
     residual
    0.81
     Supplementary
    0.80
     remainder
    0.80
     supplementary
    0.78
     IPM
    0.77
     supplemental
    0.77
    Activations Density 1.258%

    No Known Activations