© 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. 10-RES-JB
    11. 13662
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or figures with similar names starting with "Mu"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Muammar" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dispatch
    -0.71
    é¾įå
    -0.70
    姫
    -0.65
     Wizards
    -0.63
     Jonah
    -0.61
     SPACE
    -0.60
     Drift
    -0.60
     Eleven
    -0.59
     Nept
    -0.59
     Neptune
    -0.58
    POSITIVE LOGITS
    hammad
    1.51
    lder
    1.29
    ahah
    1.11
    pload
    1.11
    zik
    1.11
    jah
    1.08
    ld
    1.04
    zy
    1.02
    htar
    1.01
    lde
    1.00
    Activations Density 0.012%

    No Known Activations