© 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. 18560
    Prev
    Next
    INDEX
    Explanations

    keywords related to proximity or nearness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "close" or phrases suggesting proximity or nearing a state

    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
    */(
    -0.76
    gow
    -0.76
    æ©
    -0.73
    alis
    -0.69
    ÄŁ
    -0.69
    iple
    -0.69
    small
    -0.68
     Edited
    -0.67
    ischer
    -0.67
    among
    -0.67
    POSITIVE LOGITS
     completion
    1.14
     fruition
    1.12
     extinction
    1.09
     achieving
    1.09
     perfection
    1.04
     completing
    0.98
     reality
    0.95
     becoming
    0.93
     reaching
    0.92
     saturation
    0.92
    Activations Density 0.119%

    No Known Activations