© 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. 17079
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong emotions or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "so."

    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
     {:
    -0.65
    lihood
    -0.63
     expectancy
    -0.62
    actionDate
    -0.61
     path
    -0.60
     backdrop
    -0.59
     arrival
    -0.59
    hurst
    -0.59
     passage
    -0.59
     Peninsula
    -0.57
    POSITIVE LOGITS
    oooo
    1.11
    bered
    1.11
    ooo
    1.10
    oner
    1.03
    oths
    1.01
    othe
    1.01
    oooooooooooooooo
    0.97
    arin
    0.97
    zin
    0.95
    oooooooo
    0.92
    Activations Density 0.113%

    No Known Activations