© 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. 24555
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Moh

    oai_token-act-pair · gpt-3.5-turbo

    the name "Moh" or variations of it, often indicating a recurring subject or character in the text

    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
    ãĥ¯
    -0.88
    istics
    -0.77
     balloons
    -0.75
    istically
    -0.72
    chnology
    -0.72
    ãģ®éŃĶ
    -0.66
     Fiesta
    -0.65
    CLUS
    -0.64
    backer
    -0.64
     balloon
    -0.63
    POSITIVE LOGITS
    awk
    1.36
    awks
    1.26
    undai
    1.05
    doms
    1.01
    sin
    0.99
    renheit
    0.98
    abit
    0.97
    ira
    0.95
    atche
    0.91
    azard
    0.90
    Activations Density 0.011%

    No Known Activations