© 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. 11-RES-JB
    11. 7531
    Prev
    Next
    INDEX
    Explanations

    phrases relating to historical dating or origins

    oai_token-act-pair · gpt-3.5-turbo

    references to historical dates and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ims
    -0.71
    ressed
    -0.67
    ocal
    -0.67
    osite
    -0.67
    resses
    -0.66
    few
    -0.65
    osed
    -0.65
    ooth
    -0.65
    essen
    -0.65
    potion
    -0.64
    POSITIVE LOGITS
     antiquity
    1.33
     prehistoric
    1.16
     earliest
    1.13
     infancy
    1.08
     ancient
    1.05
     Aristotle
    0.99
     medieval
    0.98
     1928
    0.93
     colonial
    0.91
     1935
    0.90
    Activations Density 0.123%

    No Known Activations