© 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. 2-RES-JB
    11. 18951
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "plat" or derivatives such as "platinum" or "plateau."

    oai_token-act-pair · gpt-3.5-turbo

    words and terms related to "plat" or "plains."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hig
    -0.75
    glomer
    -0.74
    interstitial
    -0.71
     scissors
    -0.63
    PRES
    -0.63
     adm
    -0.62
    IVERS
    -0.61
    ugu
    -0.61
     medd
    -0.61
    CVE
    -0.61
    POSITIVE LOGITS
    plain
    1.13
    \\\\\\\\
    1.05
     plat
    1.00
     Plat
    0.96
    onic
    0.89
    yp
    0.84
    itudes
    0.84
     Niet
    0.82
     Parenthood
    0.81
    email
    0.80
    Activations Density 0.020%

    No Known Activations