© 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. 5060
    Prev
    Next
    INDEX
    Explanations

    words related to comparison or standard-setting, especially in financial or product evaluation contexts

    oai_token-act-pair · gpt-3.5-turbo

    the term "benchmark" in various contexts

    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
    agan
    -0.78
    kn
    -0.78
    oho
    -0.75
    por
    -0.73
    oles
    -0.72
    phal
    -0.71
    urses
    -0.71
    urate
    -0.70
    asive
    -0.70
    ousy
    -0.69
    POSITIVE LOGITS
     benchmark
    1.29
     benchmarks
    1.25
     indices
    0.87
    ãĤ¼ãĤ¦ãĤ¹
    0.82
     glim
    0.81
    marks
    0.78
     metrics
    0.74
    ãĥ¼ãĥĨ
    0.73
     guiActiveUnfocused
    0.72
    Bench
    0.71
    Activations Density 0.006%

    No Known Activations