© 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. 22501
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lowered" in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the action of lowering or reducing something

    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
    present
    -0.73
    icity
    -0.69
    Pac
    -0.69
    ious
    -0.68
     Machina
    -0.67
    lies
    -0.67
    Pros
    -0.66
    iott
    -0.65
    eur
    -0.65
    ¯¯
    -0.64
    POSITIVE LOGITS
     lowering
    0.90
     inhib
    0.89
    baugh
    0.86
    hetically
    0.82
    imar
    0.81
    down
    0.80
     lowered
    0.77
     guiActiveUn
    0.76
    aution
    0.75
    xual
    0.74
    Activations Density 0.007%

    No Known Activations