© 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. 7-RES-JB
    11. 18040
    Prev
    Next
    INDEX
    Explanations

    instances of the word "were" followed by additional context

    oai_token-act-pair · gpt-3.5-turbo

    the past tense form of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iates
    -0.73
    lag
    -0.69
    oire
    -0.66
    izes
    -0.65
    rouse
    -0.64
     Scrib
    -0.63
    itus
    -0.63
    iator
    -0.62
    lev
    -0.60
    place
    -0.60
    POSITIVE LOGITS
    wolves
    1.59
    wolf
    1.27
     able
    1.05
     unable
    0.95
    senal
    0.91
     subjected
    0.91
     supposed
    0.91
     instrumental
    0.91
    nt
    0.89
     originally
    0.85
    Activations Density 0.192%

    No Known Activations