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

    Neuronpedia

    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. 1-RES-JB
    11. 20265
    Prev
    Next
    INDEX
    Explanations

    numbers related to financial reporting, such as earnings and revenue figures

    oai_token-act-pair · gpt-3.5-turbo

    references to financial quarterly reports and earnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aine
    -0.85
    rome
    -0.79
    bern
    -0.79
    ÑĢ
    -0.76
    ̶
    -0.75
    Jenn
    -0.73
    AME
    -0.72
    humans
    -0.72
    leon
    -0.71
    ENE
    -0.71
    POSITIVE LOGITS
     quarterly
    1.27
    urnal
    1.18
    iann
    0.88
     earnings
    0.85
     installments
    0.84
     periodic
    0.84
     monthly
    0.82
    ounced
    0.82
     briefings
    0.81
    ouble
    0.80
    Activations Density 0.006%

    No Known Activations