© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 761
    Prev
    Next
    INDEX
    Explanations

    the acronym "UCLA."

    oai_token-act-pair · gpt-4-turbo

    mentions of a specific university, UCLA

    oai_token-act-pair · gpt-3.5-turbo

    mentions of UCLA and related organizations

    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
    BOOK
    -0.75
    DonaldTrump
    -0.75
    ocene
    -0.70
    odic
    -0.70
    ote
    -0.68
    addons
    -0.68
    ãĥĥãĥĪ
    -0.67
    horse
    -0.66
    ravings
    -0.65
    ulatory
    -0.65
    POSITIVE LOGITS
     UCLA
    1.13
     Bruins
    1.04
     Rosenberg
    0.92
    CLA
    0.81
     USC
    0.81
    UC
    0.81
     University
    0.80
    enthal
    0.80
     Extension
    0.79
     Mutual
    0.77
    Activations Density 0.005%

    No Known Activations