© 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. 20481
    Prev
    Next
    INDEX
    Explanations

    the word "was" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was."

    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
     entails
    -0.75
     Which
    -0.74
     Previous
    -0.71
    inav
    -0.67
    Vote
    -0.66
    Make
    -0.65
    ð
    -0.65
    eers
    -0.62
     Highlands
    -0.61
    exist
    -0.61
    POSITIVE LOGITS
     able
    1.04
    nt
    0.97
     supposed
    0.95
    wolf
    0.95
    wolves
    0.93
     bitten
    0.93
    hes
    0.90
     born
    0.85
     unable
    0.83
     adamant
    0.83
    Activations Density 0.351%

    No Known Activations