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. 0-RES-JB
    6. 15958
    Prev
    Next
    INDEX
    Explanations

    financial figures in the form of numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations or statistics related to financial data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.75
    ark
    -0.74
    ider
    -0.72
    quist
    -0.71
     scholarships
    -0.66
     Swordsman
    -0.65
    onson
    -0.64
    mith
    -0.63
     Maur
    -0.63
    taboola
    -0.62
    POSITIVE LOGITS
    36
    1.90
     36
    1.77
     56
    1.41
     366
    1.40
     96
    1.40
    96
    1.39
    76
    1.38
    56
    1.36
     336
    1.35
     106
    1.33
    Activations Density 0.063%

    No Known Activations