© 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. 20206
    Prev
    Next
    INDEX
    Explanations

    instances of the word "was" in past tense phrases

    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
     Mountains
    -0.61
    Make
    -0.60
     Which
    -0.60
    Footnote
    -0.60
     Individuals
    -0.59
     Hitch
    -0.59
    lev
    -0.58
    know
    -0.58
     Extend
    -0.58
     floats
    -0.58
    POSITIVE LOGITS
    hes
    1.20
    nt
    0.99
    hers
    0.97
    wolves
    0.95
    wolf
    0.91
     supposed
    0.90
     originally
    0.88
     deemed
    0.86
     able
    0.85
     indeed
    0.83
    Activations Density 0.471%

    No Known Activations