© 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. 4-RES-JB
    11. 20748
    Prev
    Next
    INDEX
    Explanations

    names or words resembling names, potentially focusing on the letter pattern "wer"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wer" in various contexts

    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
    ortium
    -0.77
    UAL
    -0.70
    ividual
    -0.68
     reinforcement
    -0.64
    itionally
    -0.59
     constit
    -0.59
     Monarch
    -0.56
     rive
    -0.56
     predatory
    -0.55
     irresistible
    -0.55
    POSITIVE LOGITS
    ijn
    1.05
    ijk
    0.90
    riter
    0.88
    baum
    0.88
    pees
    0.87
    tyard
    0.85
    pee
    0.84
    nesday
    0.83
    fare
    0.83
    ridor
    0.82
    Activations Density 0.012%

    No Known Activations