© 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. 29
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts, tensions, and power struggles

    oai_token-act-pair · gpt-3.5-turbo

    references to ongoing situations or states

    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
    endif
    -0.77
    ÑĮ
    -0.76
    wat
    -0.73
     Miko
    -0.73
     è£ıè
    -0.72
    ICO
    -0.72
    llor
    -0.70
    dad
    -0.70
    estate
    -0.68
    Econom
    -0.68
    POSITIVE LOGITS
     hopes
    1.22
     order
    1.19
     pursuit
    1.17
     preparation
    1.09
     search
    1.04
     varying
    1.04
     unprecedented
    0.99
     addition
    0.99
     unison
    0.97
     tandem
    0.97
    Activations Density 0.261%

    No Known Activations