© 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. 13736
    Prev
    Next
    INDEX
    Explanations

    references to the term "Com" or "Comrade" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Com" or related entities

    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
     Kubrick
    -0.81
     harbor
    -0.70
     Icelandic
    -0.68
     halfway
    -0.68
     dwar
    -0.65
     Mara
    -0.65
     Keynes
    -0.63
     infringing
    -0.62
     circle
    -0.61
     Kund
    -0.61
    POSITIVE LOGITS
    fortable
    1.24
    pletion
    1.21
    pleting
    1.18
    mented
    1.17
    ptroller
    1.15
    plex
    1.12
    rade
    1.05
    plete
    1.05
    intern
    1.04
    puters
    1.04
    Activations Density 0.015%

    No Known Activations