© 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. 8-RES-JB
    11. 2264
    Prev
    Next
    INDEX
    Explanations

    statements with actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding political and social actions or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brill
    -0.58
     embr
    -0.49
     Manufacturer
    -0.47
     brav
    -0.47
     glitter
    -0.47
     Shepard
    -0.46
     swast
    -0.45
     puff
    -0.45
     pat
    -0.45
     neigh
    -0.45
    POSITIVE LOGITS
    Western
    0.54
    LCS
    0.53
    anu
    0.52
    anamo
    0.51
    Beta
    0.50
    YC
    0.50
    thirds
    0.49
    Solution
    0.49
    osite
    0.49
    alla
    0.49
    Activations Density 0.528%

    No Known Activations