© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 3174
    Prev
    Next
    INDEX
    Explanations

    percentage and numerical data

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly in the context of percentages and rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     predec
    -0.59
     parach
    -0.57
     optics
    -0.56
     Proud
    -0.52
     mamm
    -0.52
     entreprene
    -0.51
     philos
    -0.50
     manufact
    -0.50
     expanding
    -0.50
     aisle
    -0.50
    POSITIVE LOGITS
    5
    1.27
    6
    1.24
    8
    1.24
    9
    1.22
    7
    1.22
    0
    1.19
    95
    1.18
    06
    1.17
    05
    1.17
    93
    1.17
    Activations Density 0.082%

    No Known Activations