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. 1-RES-JB
    6. 1890
    Prev
    Next
    INDEX
    Explanations

    formulas or mathematical expressions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "formula" with various associated meanings

    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
    usters
    -0.77
    ividual
    -0.73
     Intellectual
    -0.64
    ereo
    -0.63
    fram
    -0.60
     Links
    -0.59
    uckles
    -0.59
     Gri
    -0.58
    iere
    -0.58
     RTX
    -0.58
    POSITIVE LOGITS
     formula
    1.52
     formulas
    1.32
     formulation
    0.89
     Formula
    0.84
     formulations
    0.78
     equation
    0.72
     notation
    0.72
     linem
    0.69
    onite
    0.68
     interpol
    0.67
    Activations Density 0.008%

    No Known Activations