© 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. 23601
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to the word "niche."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specialized or niche markets and 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
     largeDownload
    -0.70
    Fac
    -0.66
    aina
    -0.66
    tein
    -0.66
    onz
    -0.66
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.63
    agher
    -0.63
    owitz
    -0.62
    HOME
    -0.62
    actionDate
    -0.61
    POSITIVE LOGITS
     niche
    1.36
    odox
    0.72
     nic
    0.71
    escent
    0.70
     proble
    0.70
     outlet
    0.70
     darling
    0.69
    markets
    0.67
    ulously
    0.67
     Chimera
    0.66
    Activations Density 0.006%

    No Known Activations