© 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. 22304
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific name or brand ('Clar')

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "clarify."

    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
    MET
    -0.79
    FAULT
    -0.71
    WAYS
    -0.68
    ORGE
    -0.67
    ETF
    -0.66
    STEM
    -0.65
     Awakens
    -0.65
    ħĭ
    -0.64
    ï¸
    -0.64
     Pants
    -0.61
    POSITIVE LOGITS
    inet
    1.42
    ifying
    1.39
    ifications
    1.32
    ifies
    1.23
    ifier
    1.16
    ifiers
    1.16
    ific
    1.14
    ified
    1.12
     clar
    1.08
    issa
    1.05
    Activations Density 0.013%

    No Known Activations