© 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. 2-RES-JB
    6. 352
    Prev
    Next
    INDEX
    Explanations

    words indicating illumination or clarity, and numeric quantification or measurement

    oai_token-act-pair · gpt-4-turbo

    words related to investigative reporting or uncovering hidden information

    oai_token-act-pair · gpt-3.5-turbo

    popular movie titles along with their box office earnings

    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
     referen
    -0.50
     [|
    -0.39
     redistributed
    -0.39
    Tokens
    -0.39
    $$$$
    -0.39
    ĪĴ
    -0.38
    idated
    -0.37
     equivalents
    -0.37
    Discussion
    -0.37
     Moroc
    -0.36
    POSITIVE LOGITS
    NetMessage
    0.50
     largeDownload
    0.43
     DRAGON
    0.43
    terness
    0.43
    taboola
    0.41
    pin
    0.39
    conom
    0.37
    utions
    0.37
    othes
    0.37
    brew
    0.36
    Activations Density 7.644%

    No Known Activations