© 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. 2224
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Linden"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lind."

    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
    OPLE
    -0.81
    Ø©
    -0.73
    Magikarp
    -0.64
     inhibitors
    -0.63
    ORTS
    -0.61
     actionGroup
    -0.60
    ================================================================
    -0.58
     diaper
    -0.57
     Franch
    -0.56
    OURCE
    -0.56
    POSITIVE LOGITS
    strom
    1.35
    gren
    1.34
    say
    1.22
    quist
    1.22
    isf
    1.14
    holm
    1.12
    enberg
    1.12
    ahl
    1.10
    en
    1.09
    enstein
    1.05
    Activations Density 0.036%

    No Known Activations