© 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. 18513
    Prev
    Next
    INDEX
    Explanations

    statements related to someone's current situation or actions

    oai_token-act-pair · gpt-3.5-turbo

    statements about future intentions or predictions

    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
    Recommend
    -0.73
     unison
    -0.68
    >:
    -0.67
     yourselves
    -0.66
    umer
    -0.66
     %%
    -0.64
     <[
    -0.64
    aspx
    -0.64
     âĹ
    -0.64
    eps
    -0.63
    POSITIVE LOGITS
     his
    1.38
     he
    1.34
     himself
    1.08
    his
    0.98
    His
    0.96
    He
    0.86
     He
    0.85
     quitting
    0.84
     His
    0.77
     stint
    0.73
    Activations Density 0.742%

    No Known Activations