© 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. 10612
    Prev
    Next
    INDEX
    Explanations

    information about events, releases, or updates related to technology products and software

    oai_token-act-pair · gpt-3.5-turbo

    contextual markers related to events or announcements

    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
    Newsletter
    -0.77
    izen
    -0.76
    istical
    -0.74
     WATCHED
    -0.71
    ¬¼
    -0.69
    obyl
    -0.64
    imal
    -0.64
    oir
    -0.62
    weak
    -0.61
    isms
    -0.60
    POSITIVE LOGITS
     featuring
    1.13
     showcasing
    1.07
    feat
    0.98
     courtesy
    0.96
     confirming
    0.93
     revealing
    0.93
     wherein
    0.92
     bringing
    0.89
     allowing
    0.89
     highlighting
    0.87
    Activations Density 0.342%

    No Known Activations