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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 19248
    Prev
    Next
    INDEX
    Explanations

    words related to money or financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial expenditures or outlays

    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
     cla
    -0.77
     boun
    -0.76
     sore
    -0.72
     accommodating
    -0.71
     unloaded
    -0.69
    abus
    -0.69
    alty
    -0.69
    hab
    -0.68
     spacious
    -0.67
     bite
    -0.67
    POSITIVE LOGITS
    EStream
    0.86
    DragonMagazine
    0.86
    gaard
    0.80
    WER
    0.76
    âĶģ
    0.76
    ibrary
    0.75
    vantage
    0.75
    sers
    0.74
    pedia
    0.74
    llor
    0.73
    Activations Density 0.020%

    No Known Activations