© 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. 4-RES-JB
    11. 6454
    Prev
    Next
    INDEX
    Explanations

    numerical values related to costs and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and cost-related information

    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
     pse
    -0.41
    Reviewer
    -0.39
     Plasma
    -0.34
     Archer
    -0.33
     guitarist
    -0.33
    laws
    -0.33
    rist
    -0.32
    recated
    -0.32
    venge
    -0.31
     Vulkan
    -0.31
    POSITIVE LOGITS
     apiece
    0.69
     pounds
    0.57
     lbs
    0.50
    lbs
    0.50
    pees
    0.49
     per
    0.49
     percent
    0.48
     kilograms
    0.47
    million
    0.46
     hectares
    0.46
    Activations Density 0.927%

    No Known Activations