© 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. 9-RES-JB
    11. 15771
    Prev
    Next
    INDEX
    Explanations

    solutions or answers to various problems or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    various terms related to solutions, remedies, and answers to problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ographs
    -0.74
    prints
    -0.73
     livest
    -0.70
    aturdays
    -0.67
     cloves
    -0.67
     mushrooms
    -0.66
     Cous
    -0.64
     cous
    -0.63
    gian
    -0.63
    ographies
    -0.59
    POSITIVE LOGITS
     solution
    1.00
     remedy
    0.90
    Solution
    0.88
    acea
    0.81
     whereby
    0.79
     solutions
    0.78
     Solution
    0.72
     Approach
    0.71
    olution
    0.71
     antidote
    0.70
    Activations Density 0.129%

    No Known Activations