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. 4-RES-JB
    6. 18901
    Prev
    Next
    INDEX
    Explanations

    words related to numbers, especially when it comes to quantification or mathematical operations

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values or quantities

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

    No Comments

    Negative Logits
    rador
    -1.16
    ovie
    -0.76
    hire
    -0.76
    INTON
    -0.76
    robe
    -0.74
    rait
    -0.70
    Interstitial
    -0.69
    erate
    -0.68
    ossier
    -0.68
    clair
    -0.68
    POSITIVE LOGITS
     digits
    0.81
    plates
    0.80
    ames
    0.77
     Numbers
    0.72
     milliseconds
    0.69
    codes
    0.69
     numer
    0.69
    metry
    0.68
     comput
    0.68
    ology
    0.67
    Activations Density 0.036%

    No Known Activations