© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 5020
    Prev
    Next
    INDEX
    Explanations

    specific references to past events or actions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    the word 'that' in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    pee
    -0.76
    sbm
    -0.76
    ãĥĥãĥĪ
    -0.76
    roid
    -0.75
    è¦ļéĨĴ
    -0.74
    ocus
    -0.73
    ãĥ¯ãĥ³
    -0.72
    oco
    -0.72
    %%%%
    -0.72
    Edge
    -0.71
    POSITIVE LOGITS
     day
    1.76
     evening
    1.63
     night
    1.61
     afternoon
    1.59
     morning
    1.58
     fateful
    1.53
     year
    1.37
     month
    1.36
     week
    1.32
     weekend
    1.27
    Activations Density 0.150%

    No Known Activations