© 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. 8-RES-JB
    11. 6995
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to the term "Mes"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Mes" and "meson," indicating a focus on particle physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yankee
    -0.69
     breakup
    -0.68
     ASC
    -0.67
    Reviewer
    -0.65
     skate
    -0.65
    cake
    -0.62
     Bened
    -0.60
    ICE
    -0.60
     Bruins
    -0.59
     axe
    -0.59
    POSITIVE LOGITS
    quite
    1.44
    opot
    1.30
    olithic
    1.04
    ultan
    0.99
    hing
    0.96
    omorphic
    0.96
    omorph
    0.94
    earchers
    0.94
    ophon
    0.94
    nil
    0.93
    Activations Density 0.040%

    No Known Activations