© 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. 3-RES-JB
    11. 4951
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Lind" with varying numbers accompanying it

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Lind" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.90
    CLASSIFIED
    -0.78
    Magikarp
    -0.75
    ABLE
    -0.68
    avez
    -0.65
    Ø©
    -0.65
    ASED
    -0.64
    Ultimate
    -0.64
    ably
    -0.62
    éŃĶ
    -0.61
    POSITIVE LOGITS
    gren
    1.22
    strom
    1.11
    enstein
    1.01
    quist
    1.00
    isf
    1.00
    ahl
    1.00
    seys
    1.00
    berg
    0.99
    lasses
    0.92
    stad
    0.90
    Activations Density 0.008%

    No Known Activations