© 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. 9-RES-JB
    11. 15687
    Prev
    Next
    INDEX
    Explanations

    occurances of words related to dispersion or distribution

    oai_token-act-pair · gpt-3.5-turbo

    references to the distribution or arrangement of objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fight
    -0.80
    ibur
    -0.74
    asus
    -0.71
    bara
    -0.69
    ocene
    -0.68
    Trade
    -0.68
    sen
    -0.67
    geons
    -0.65
    obar
    -0.64
    Demand
    -0.63
    POSITIVE LOGITS
     scattered
    1.09
    mble
    0.87
     scattering
    0.84
     dispersed
    0.83
     assemb
    0.83
     assortment
    0.77
     remnants
    0.76
     throughout
    0.75
     belongings
    0.75
    ly
    0.74
    Activations Density 0.149%

    No Known Activations