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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 8954
    Prev
    Next
    INDEX
    Explanations

    economic and financial data points expressed as percentages or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and data related to economic metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     edited
    -0.62
     Jury
    -0.60
     goodbye
    -0.59
     Metatron
    -0.58
     dab
    -0.57
     duct
    -0.57
     suscept
    -0.56
     Kaf
    -0.56
     ABE
    -0.55
     eternity
    -0.55
    POSITIVE LOGITS
    pc
    1.22
    %,
    1.17
    %-
    1.16
    %
    1.11
     percent
    1.11
    %;
    1.08
    %.
    1.06
    bps
    1.04
    %:
    1.03
    %"
    1.02
    Activations Density 0.087%

    No Known Activations