© 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. 1-RES-JB
    11. 5035
    Prev
    Next
    INDEX
    Explanations

    phrases related to passing or crossing in a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to various forms of "pass" and specific proper nouns connected to politics or local contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CMS
    -0.70
    inator
    -0.67
     rehabilit
    -0.62
    ãĥĺãĥ©
    -0.62
    itarian
    -0.61
    adeon
    -0.60
     servicing
    -0.60
     analogy
    -0.59
     redesign
    -0.59
     Drupal
    -0.59
    POSITIVE LOGITS
    renheit
    0.94
    raq
    0.81
    ppo
    0.78
    OPLE
    0.77
    irin
    0.75
     Leth
    0.75
    DAY
    0.73
    growth
    0.72
     Hof
    0.72
    EXT
    0.72
    Activations Density 0.038%

    No Known Activations