© 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. 9-RES-JB
    11. 15451
    Prev
    Next
    INDEX
    Explanations

    verbs related to performing actions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating conditions or alternatives

    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
    lass
    -0.71
    sted
    -0.65
    apsed
    -0.64
    Ö¼
    -0.63
    payer
    -0.63
     Hopkins
    -0.63
    lucent
    -0.60
    rained
    -0.60
    lex
    -0.58
     Believe
    -0.58
    POSITIVE LOGITS
     amusement
    1.10
     souven
    1.00
     purposes
    0.98
     entertainment
    0.90
     decoration
    0.90
     aiding
    0.84
     assisting
    0.84
     enjoyment
    0.81
     emergencies
    0.79
     gratification
    0.78
    Activations Density 0.420%

    No Known Activations