© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 21742
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas or expressions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "formula" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    watching
    -0.68
    walking
    -0.63
    ucket
    -0.63
    fram
    -0.62
    avorable
    -0.62
    OUT
    -0.62
     Gri
    -0.61
     Hands
    -0.60
     perspect
    -0.60
     [+
    -0.59
    POSITIVE LOGITS
     formula
    1.15
     formulas
    1.12
    anus
    0.85
    sis
    0.78
    onite
    0.77
    rition
    0.77
     equations
    0.74
     Formula
    0.74
    ted
    0.74
     formulation
    0.73
    Activations Density 0.032%

    No Known Activations