© 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. 11224
    Prev
    Next
    INDEX
    Explanations

    specific dates and events mentioned in a formal context

    oai_token-act-pair · gpt-3.5-turbo

    references to news articles or publications

    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
     lately
    -0.85
     nowadays
    -0.77
     tomorrow
    -0.75
    =-=-=-=-
    -0.73
     tho
    -0.73
     tonight
    -0.73
    >,
    -0.71
     someday
    -0.69
     though
    -0.69
    )?
    -0.68
    POSITIVE LOGITS
     began
    0.90
     erupted
    0.89
     flew
    0.81
     became
    0.80
     appeared
    0.79
     awoke
    0.79
     consisted
    0.77
     ceased
    0.75
     collided
    0.75
     surfaced
    0.73
    Activations Density 0.613%

    No Known Activations