© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6387
    Prev
    Next
    INDEX
    Explanations

    phrases where an action is being taken or a new system is being created

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intention or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Finished
    -0.67
    standing
    -0.65
    living
    -0.63
     misses
    -0.62
     loving
    -0.62
     Plain
    -0.60
    quickShipAvailable
    -0.59
     kisses
    -0.58
     smiles
    -0.58
     Passion
    -0.58
    POSITIVE LOGITS
     facilitate
    1.33
     encourage
    1.28
     commemorate
    1.25
     assist
    1.24
     ensure
    1.23
     promote
    1.23
     accompany
    1.23
     simplify
    1.22
     counteract
    1.22
     regulate
    1.22
    Activations Density 0.181%

    No Known Activations