© 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. 17438
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mos" at different activation levels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mos" or variations thereof

    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
    ACTED
    -0.75
    istical
    -0.73
    DragonMagazine
    -0.72
    ordinate
    -0.72
    ISM
    -0.70
    STEP
    -0.69
    Accessory
    -0.69
    istically
    -0.68
    sburgh
    -0.67
    istics
    -0.66
    POSITIVE LOGITS
    illion
    0.88
    fet
    0.83
    ques
    0.83
    cos
    0.83
    bat
    0.82
     Mos
    0.82
    cone
    0.81
    quit
    0.80
    hin
    0.79
    erver
    0.79
    Activations Density 0.005%

    No Known Activations