© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 20165
    Prev
    Next
    INDEX
    Explanations

    exclamation marks and brief phrases indicating high emotion or urgency

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and intervals in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     drawn
    -0.83
     mutually
    -0.81
     camp
    -0.81
     describ
    -0.81
     undecided
    -0.80
     exiled
    -0.79
     dialect
    -0.77
     decisive
    -0.74
     tro
    -0.74
     sculpt
    -0.74
    POSITIVE LOGITS
    Companies
    1.50
    Avoid
    1.41
    Imagine
    1.37
    Posted
    1.33
    Learn
    1.32
    Why
    1.32
    Researchers
    1.31
    Sometimes
    1.31
    Have
    1.28
    You
    1.28
    Activations Density 0.509%

    No Known Activations