© 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. 10-RES-JB
    11. 8581
    Prev
    Next
    INDEX
    Explanations

    action verbs in progressive tense

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to conflict or struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     representations
    -0.71
    ECD
    -0.67
     Preservation
    -0.63
     Monetary
    -0.63
     Responsibility
    -0.63
    attribute
    -0.62
    orthy
    -0.62
    saf
    -0.61
    DI
    -0.60
    soever
    -0.60
    POSITIVE LOGITS
     snowball
    1.50
     escalated
    1.33
     dwind
    1.33
     escalate
    1.25
     progressed
    1.25
     spir
    1.22
     progresses
    1.18
     escal
    1.16
     bloss
    1.15
     CONTIN
    1.13
    Activations Density 0.557%

    No Known Activations