© 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. 8582
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning of a message or section

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts

    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
    FontSize
    -0.74
    CVE
    -0.68
    hered
    -0.67
    amiya
    -0.66
    ibly
    -0.65
    onse
    -0.65
     unsuccessfully
    -0.64
     indeed
    -0.62
    here
    -0.62
    orters
    -0.61
    POSITIVE LOGITS
     latest
    1.13
     Recipe
    1.05
     Latest
    1.00
     scoop
    0.80
     hottest
    0.78
     FREE
    0.76
     roundup
    0.74
     411
    0.72
     daily
    0.72
     Updates
    0.71
    Activations Density 0.034%

    No Known Activations