© 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. 11-RES-JB
    6. 22126
    Prev
    Next
    INDEX
    Explanations

    words related to speed, efficiency, and control in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    statements related to numeric values and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ador
    -0.69
    rique
    -0.69
     openings
    -0.64
     awaits
    -0.64
    ventures
    -0.63
     tongues
    -0.62
    NetMessage
    -0.61
    kids
    -0.61
     Awakens
    -0.61
     Finish
    -0.59
    POSITIVE LOGITS
     proportional
    1.52
     determined
    1.24
     adjustable
    1.19
     dependent
    1.12
     negligible
    1.08
     dictated
    1.07
     minimized
    1.07
     measured
    1.07
     calculated
    1.05
     predetermined
    1.04
    Activations Density 0.228%

    No Known Activations