© 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. 7-RES-JB
    11. 19269
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or processes that are ongoing or uninterrupted

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing or repeated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.81
    ooters
    -0.77
    atana
    -0.75
    dinand
    -0.75
    ographical
    -0.75
    ustomed
    -0.74
    iah
    -0.72
    ool
    -0.72
    és
    -0.72
    acus
    -0.70
    POSITIVE LOGITS
     unab
    0.95
     uninterrupted
    0.81
     unchanged
    0.78
     ap
    0.76
     indefinitely
    0.76
     unravel
    0.70
     tremend
    0.69
     unanswered
    0.68
     vitality
    0.68
     churn
    0.67
    Activations Density 0.041%

    No Known Activations