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. 11-RES-JB
    6. 10376
    Prev
    Next
    INDEX
    Explanations

    financial data and statistics

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases related to statistics and numerical data

    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
     volunte
    -0.98
     skelet
    -0.93
    ĸļ
    -0.90
    »Ĵ
    -0.87
     affili
    -0.86
     carbohyd
    -0.83
     surg
    -0.83
    ĪĴ
    -0.82
     estab
    -0.82
     shaming
    -0.82
    POSITIVE LOGITS
     Overall
    1.48
     Prices
    1.37
     Average
    1.36
     Rates
    1.36
     Adjusted
    1.34
     Meanwhile
    1.34
     Compared
    1.32
    Average
    1.30
    Overall
    1.29
    Total
    1.21
    Activations Density 0.263%

    No Known Activations