© 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. 3-RES-JB
    11. 1810
    Prev
    Next
    INDEX
    Explanations

    contexts where things are evenly or unevenly distributed

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evenness and division in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.83
    OLOG
    -0.81
    ger
    -0.76
    gers
    -0.75
    eur
    -0.73
    href
    -0.72
    GER
    -0.70
    ourke
    -0.68
    isms
    -0.67
     inaction
    -0.67
    POSITIVE LOGITS
     evenly
    1.06
     spaced
    1.06
     ILCS
    0.99
     distribute
    0.89
     proport
    0.86
     divided
    0.86
     sized
    0.86
     dispersed
    0.82
     distributed
    0.82
     disperse
    0.82
    Activations Density 0.015%

    No Known Activations