© 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. 1-RES-JB
    11. 22954
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "low"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "low" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mahjong
    -0.77
    tnc
    -0.76
    andise
    -0.76
    arium
    -0.75
    thus
    -0.74
    Maps
    -0.74
     Orient
    -0.73
    OGR
    -0.71
    æѦ
    -0.71
    Advertisements
    -0.70
    POSITIVE LOGITS
     dipping
    0.91
     low
    0.80
     enough
    0.79
    stairs
    0.78
    ens
    0.76
     grazing
    0.74
     paced
    0.73
    est
    0.73
    lighting
    0.73
    ened
    0.72
    Activations Density 0.020%

    No Known Activations