© 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. 1-RES-JB
    6. 6512
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the name "Mes"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual, likely a public figure or celebrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffee
    -0.76
    shapeshifter
    -0.70
    cake
    -0.68
    ãģĮ
    -0.66
    éĸ
    -0.64
    aneers
    -0.63
    å£
    -0.63
     Vanguard
    -0.63
    boarding
    -0.63
     ASC
    -0.62
    POSITIVE LOGITS
     Mes
    1.24
    opot
    1.02
    quite
    0.88
    ilit
    0.81
    uve
    0.79
     indo
    0.77
    cil
    0.77
    olithic
    0.77
    seys
    0.76
    omorph
    0.75
    Activations Density 0.003%

    No Known Activations