© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 12272
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific individual named "Kal-ema-Zikusoka"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Kalemazik."

    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
     feature
    -0.66
     months
    -0.64
     repe
    -0.64
     cache
    -0.62
     Der
    -0.61
     depreciation
    -0.60
     Tottenham
    -0.60
     charg
    -0.60
     mort
    -0.59
     lifetime
    -0.59
    POSITIVE LOGITS
    oka
    4.94
    oko
    1.33
    oki
    1.31
    ok
    1.21
    oku
    1.20
    oga
    1.19
    ako
    1.16
    uku
    1.10
    oya
    1.10
    aho
    1.08
    Activations Density 0.011%

    No Known Activations