© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14161
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Lad" at varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names that start with "Lad" and "Glad."

    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
    ELL
    -0.93
    EED
    -0.78
    REE
    -0.70
    ä¸Ń
    -0.68
    natureconservancy
    -0.67
     compounded
    -0.65
    displayText
    -0.65
     Citadel
    -0.63
    CHAT
    -0.62
     ticking
    -0.62
    POSITIVE LOGITS
    imir
    1.41
    lad
    1.21
    der
    1.13
    ynam
    0.98
    isl
    0.98
    iamond
    0.97
    osaurs
    0.89
    mir
    0.87
    withstanding
    0.83
    imer
    0.83
    Activations Density 0.008%

    No Known Activations