© 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. 18327
    Prev
    Next
    INDEX
    Explanations

    references to the term "Un" with some following attributes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term 'Un' in various contexts, possibly indicating a focus on union-related topics

    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
    OPLE
    -1.06
    Ö¼
    -0.82
    anwhile
    -0.81
    utical
    -0.79
    hetti
    -0.76
    ij士
    -0.75
     Madden
    -0.75
    Ó
    -0.75
    Ò
    -0.74
     Dickinson
    -0.70
    POSITIVE LOGITS
    cles
    1.08
    idad
    0.97
    ruly
    0.96
    agi
    0.96
    affiliated
    0.95
    ities
    0.95
    itarian
    0.95
    balanced
    0.94
    usual
    0.91
    classified
    0.91
    Activations Density 0.013%

    No Known Activations