© 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. 6-RES-JB
    11. 13794
    Prev
    Next
    INDEX
    Explanations

    phrases related to speeding up or facilitating processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of expediting processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤº
    -0.66
    dash
    -0.66
    maker
    -0.65
    ktop
    -0.64
     Imran
    -0.64
     Maker
    -0.64
    plate
    -0.64
    cloth
    -0.62
     Pixie
    -0.61
    blank
    -0.61
    POSITIVE LOGITS
    itions
    1.35
    ited
    1.25
    ition
    1.23
    itive
    1.19
    iting
    1.12
    itional
    1.10
    itors
    1.07
    iency
    1.06
    itionally
    1.03
    itives
    1.02
    Activations Density 0.045%

    No Known Activations