© 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. 0-RES-JB
    11. 13720
    Prev
    Next
    INDEX
    Explanations

    mentions of the actor Leonardo DiCaprio

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Leonardo DiCaprio."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ket
    -0.71
     butter
    -0.65
     inflation
    -0.61
     ann
    -0.61
     neutral
    -0.61
     Canada
    -0.61
     post
    -0.58
     possession
    -0.58
     indications
    -0.57
     Spell
    -0.57
    POSITIVE LOGITS
    rio
    5.28
    rium
    1.42
    ria
    1.26
    rius
    1.24
    rious
    1.19
    riad
    1.15
    lio
    1.14
    ri
    1.11
    redo
    1.08
    rito
    1.08
    Activations Density 0.015%

    No Known Activations