© 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. 0-RES-JB
    11. 5348
    Prev
    Next
    INDEX
    Explanations

    the word "Off" with the strongest activation levels

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "off" or "offering."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izabeth
    -0.70
    ridor
    -0.64
    growth
    -0.63
     dehydration
    -0.62
     skelet
    -0.62
    ascript
    -0.61
     federation
    -0.61
    omething
    -0.60
    enment
    -0.60
    ATHER
    -0.60
    POSITIVE LOGITS
     Off
    3.65
    Off
    2.44
     OFF
    2.42
    off
    1.88
    OFF
    1.80
     off
    1.56
    offs
    1.36
     Offer
    1.33
     Away
    1.27
     Down
    1.23
    Activations Density 0.006%

    No Known Activations