© 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. 9598
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate a necessary action or step in a process

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating procedural or conditional instructions

    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
    markets
    -0.68
    didn
    -0.63
     Cornwall
    -0.62
     diapers
    -0.61
    Tea
    -0.61
    Rated
    -0.61
    Nap
    -0.60
    court
    -0.59
    Elsewhere
    -0.57
     pap
    -0.57
    POSITIVE LOGITS
     maximize
    0.93
     qualify
    0.91
     solve
    0.88
     simplify
    0.87
     properly
    0.86
     facilitate
    0.86
     succeed
    0.85
     determine
    0.83
     Activate
    0.82
     achieve
    0.82
    Activations Density 0.078%

    No Known Activations