© 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. 4-RES-JB
    11. 10402
    Prev
    Next
    INDEX
    Explanations

    strings related to "positions"

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "pose" and its related terms in different contexts

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

    No Comments

    Negative Logits
    loo
    -0.77
    lain
    -0.75
     oats
    -0.74
    sonian
    -0.71
    awei
    -0.66
    urst
    -0.66
     Clarkson
    -0.65
    lehem
    -0.65
     casc
    -0.65
    wal
    -0.64
    POSITIVE LOGITS
    xual
    1.32
    itions
    1.23
    itory
    1.21
    itional
    1.14
    itives
    1.07
    itor
    1.02
    pos
    1.02
    itionally
    0.97
    cript
    0.95
    itiveness
    0.94
    Activations Density 0.008%

    No Known Activations