© 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. 7-RES-JB
    6. 9827
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "secondary"

    oai_token-act-pair · gpt-3.5-turbo

    references to "secondary" concepts or effects

    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
    uge
    -0.82
    liness
    -0.78
    atche
    -0.77
    ===
    -0.74
    ————
    -0.72
    rike
    -0.70
    âĸĪâĸĪâĸĪâĸĪ
    -0.70
    ixels
    -0.70
    essee
    -0.69
    emi
    -0.69
    POSITIVE LOGITS
    ities
    0.86
    anguage
    0.81
    aband
    0.81
    secondary
    0.79
    arily
    0.75
     mater
    0.73
     school
    0.72
     lobe
    0.69
    school
    0.67
     estate
    0.67
    Activations Density 0.024%

    No Known Activations