© 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. 22581
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a person named "Ivan."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Van" and its related forms

    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
     NETWORK
    -0.87
     reluct
    -0.72
    ĨĴ
    -0.72
    REE
    -0.69
    ĪĴ
    -0.67
     bitters
    -0.66
    ĻĤ
    -0.65
     casc
    -0.64
    IJ
    -0.64
    ij士
    -0.63
    POSITIVE LOGITS
    van
    1.23
    igans
    1.09
    ishing
    1.07
    anth
    1.07
    igan
    0.99
    hoe
    0.94
    oline
    0.94
    loo
    0.94
    ovich
    0.92
    ron
    0.92
    Activations Density 0.006%

    No Known Activations