© 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. 8-RES-JB
    11. 7858
    Prev
    Next
    INDEX
    Explanations

    phrases containing the words "old-fashioned" followed by a variety of different words and undertakings

    oai_token-act-pair · gpt-3.5-turbo

    references to outdated ideologies or styles

    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
     Moreno
    -0.75
     sinks
    -0.74
     istg
    -0.73
     lashes
    -0.72
     proceeds
    -0.71
     moder
    -0.70
     DRAG
    -0.70
    anca
    -0.69
     latitude
    -0.69
    ï¸ı
    -0.67
    POSITIVE LOGITS
    fashioned
    1.25
    style
    1.12
    sounding
    1.09
    angled
    1.08
    looking
    1.04
    generation
    1.04
    day
    0.98
    derived
    0.95
    Soviet
    0.95
    old
    0.94
    Activations Density 0.078%

    No Known Activations