© 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. 2-RES-JB
    11. 17202
    Prev
    Next
    INDEX
    Explanations

    phrases related to universities, colleges, and academic institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to universities and the concept of ability or competence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Passage
    -0.76
     Borough
    -0.74
    ĺħ
    -0.66
    ota
    -0.65
    District
    -0.64
    letter
    -0.62
     Peninsula
    -0.62
    Ĥª
    -0.61
    ¬¼
    -0.60
     districts
    -0.59
    POSITIVE LOGITS
    ibility
    1.09
    icals
    1.08
    abil
    1.07
    icians
    1.07
    ible
    1.00
    ibles
    0.98
    ifier
    0.97
    ional
    0.97
    ually
    0.94
    ationally
    0.94
    Activations Density 0.028%

    No Known Activations