© 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. 8979
    Prev
    Next
    INDEX
    Explanations

    phrases related to putting things together or assembling

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "put together."

    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
    occ
    -0.69
     privilege
    -0.61
    cul
    -0.61
    den
    -0.61
    obi
    -0.60
    letters
    -0.60
    ounce
    -0.59
    dark
    -0.59
    ola
    -0.58
    margin
    -0.56
    POSITIVE LOGITS
    halla
    0.78
    illet
    0.75
    edo
    0.75
    é¾įå¥ij士
    0.74
    sonian
    0.73
    ÃįÃį
    0.72
    éĹĺ
    0.72
    isphere
    0.71
    Community
    0.70
    女
    0.70
    Activations Density 0.019%

    No Known Activations