© 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. 23259
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to concluding, finalizing, or bridging gaps

    oai_token-act-pair · gpt-3.5-turbo

    actions related to closing gaps or deals

    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
    CTV
    -0.80
    anse
    -0.75
    ãĥīãĥ©ãĤ´ãĥ³
    -0.75
    andise
    -0.73
    PHOTOS
    -0.69
    dayName
    -0.67
    LAND
    -0.67
    ants
    -0.67
    eday
    -0.65
    天
    -0.65
    POSITIVE LOGITS
     loopholes
    1.34
     doors
    1.04
     loophole
    0.97
     ranks
    0.96
     gaps
    0.95
     down
    0.91
     caption
    0.90
     Doors
    0.88
     curtains
    0.84
     Guant
    0.82
    Activations Density 0.049%

    No Known Activations