© 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. 4-RES-JB
    6. 22034
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names likely associated with various individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and terms related to particular names or concepts

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

    No Comments

    Negative Logits
    cook
    -0.76
    olerance
    -0.75
    OPLE
    -0.74
    phrine
    -0.73
    step
    -0.72
    KEN
    -0.69
     Handler
    -0.69
    eco
    -0.68
     Raider
    -0.68
    watch
    -0.67
    POSITIVE LOGITS
    icles
    1.22
    icle
    1.10
    icular
    0.98
    rha
    0.89
    itational
    0.87
    oras
    0.87
    ora
    0.87
    ilion
    0.85
    rix
    0.85
    ricular
    0.81
    Activations Density 0.017%

    No Known Activations