© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 5242
    Prev
    Next
    INDEX
    Explanations

    terms related to businesses and financial news, particularly related to the news show "Squawk Box" on CNBC

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Squ" and variations related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nanto
    -0.79
    vironment
    -0.76
    ocaust
    -0.75
    ãĤ´ãĥ³
    -0.72
    é¾į
    -0.71
     partName
    -0.71
     Archdemon
    -0.69
    emort
    -0.68
    ãģ®éŃĶ
    -0.68
     reconciliation
    -0.68
    POSITIVE LOGITS
    irrel
    1.19
    ares
    1.03
    Squ
    0.97
    ¹
    0.91
    atters
    0.86
    aku
    0.85
    ishable
    0.84
    bour
    0.83
    ramid
    0.82
    ishers
    0.82
    Activations Density 0.010%

    No Known Activations