© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 10446
    Prev
    Next
    INDEX
    Explanations

    the word "fresco" and terms related to data usage, most likely related to web development or IT

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of antisemitism and specific place names or terms associated with it

    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
    framework
    -0.76
    monary
    -0.74
    fman
    -0.74
    icut
    -0.73
    rities
    -0.70
    è¦ļéĨĴ
    -0.70
    rag
    -0.70
     Berks
    -0.69
    isher
    -0.69
    ratulations
    -0.68
    POSITIVE LOGITS
    hiba
    0.97
    omes
    0.78
    ï¸
    0.77
    sell
    0.77
    spect
    0.75
     mosa
    0.75
     Tac
    0.74
    ources
    0.74
    print
    0.71
    colo
    0.71
    Activations Density 0.021%

    No Known Activations