© 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. 9843
    Prev
    Next
    INDEX
    Explanations

    sentences ending in a period and consisting of multiple clauses

    oai_token-act-pair · gpt-3.5-turbo

    situations involving personal struggles or emotional distress

    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
     sustainability
    -0.78
     implementation
    -0.70
     freshwater
    -0.68
     consumer
    -0.68
     regulatory
    -0.67
     Components
    -0.67
     environmental
    -0.67
     environmentally
    -0.65
     innov
    -0.65
     wastewater
    -0.65
    POSITIVE LOGITS
    she
    0.85
    lvl
    0.84
    CHAPTER
    0.83
    Then
    0.82
    ↵Âł
    0.81
    He
    0.81
    She
    0.80
    Was
    0.80
    said
    0.79
    His
    0.77
    Activations Density 0.555%

    No Known Activations