© 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. 10-RES-JB
    6. 834
    Prev
    Next
    INDEX
    Explanations

    phrases related to the programming language "Nim."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "Nim" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.71
    ================================================================
    -0.68
    operative
    -0.63
    ++++++++++++++++
    -0.62
    acters
    -0.61
    achusetts
    -0.60
    OTT
    -0.59
    %%%%
    -0.59
    ======
    -0.58
    iov
    -0.57
    POSITIVE LOGITS
    uggets
    0.99
    daq
    0.98
    emonic
    0.91
    ominated
    0.85
    guyen
    0.81
    isance
    0.81
    elson
    0.80
    vana
    0.77
    ucle
    0.76
    jad
    0.72
    Activations Density 0.098%

    No Known Activations