© 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. 11-RES-JB
    11. 6673
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions and debates

    oai_token-act-pair · gpt-3.5-turbo

    instances of discussions, debates, or negotiations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Preservation
    -0.82
     Installation
    -0.78
     Corporation
    -0.67
     Distribut
    -0.67
     Deposit
    -0.66
     Removal
    -0.66
     Upload
    -0.66
     stocking
    -0.65
    endment
    -0.62
     representations
    -0.62
    POSITIVE LOGITS
     escalated
    1.27
     escalate
    1.25
     spir
    1.19
     snowball
    1.16
     flared
    1.16
     culmin
    1.14
     raged
    1.13
     heated
    1.11
     escal
    1.09
     culminated
    1.08
    Activations Density 0.246%

    No Known Activations