© 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. 8-RES-JB
    6. 2059
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods, particularly the 19th and 20th centuries

    oai_token-act-pair · gpt-3.5-turbo

    negative references to centuries, particularly focusing on the 19th and 20th centuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BILITIES
    -0.67
    EStream
    -0.65
    xit
    -0.62
     yours
    -0.61
     Logged
    -0.61
     Powder
    -0.60
    raltar
    -0.60
     Misc
    -0.59
     powd
    -0.58
     Rwanda
    -0.57
    POSITIVE LOGITS
    century
    1.38
    hour
    0.93
    teenth
    0.88
    eyed
    0.82
    ennial
    0.80
    ann
    0.79
    inch
    0.79
    percent
    0.77
     century
    0.77
    ursday
    0.75
    Activations Density 0.078%

    No Known Activations