© 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. 3-RES-JB
    11. 3224
    Prev
    Next
    INDEX
    Explanations

    proper nouns with "van" in them

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Van" and its variations

    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
     reluct
    -0.84
     NETWORK
    -0.82
     casc
    -0.65
     Seym
    -0.64
    IJ
    -0.64
    mable
    -0.62
    inals
    -0.62
     surpr
    -0.61
    ĨĴ
    -0.61
     bitters
    -0.60
    POSITIVE LOGITS
    van
    1.05
    ishing
    1.02
    anth
    1.01
    loo
    0.94
    hoe
    0.94
    igans
    0.91
    illa
    0.87
    ishment
    0.87
    quez
    0.87
    adium
    0.86
    Activations Density 0.004%

    No Known Activations