© 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. 12629
    Prev
    Next
    INDEX
    Explanations

    specific numerical values within a certain range

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those related to measurements or financial amounts

    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
     Dragonbound
    -0.80
    psey
    -0.80
    eals
    -0.79
    ipt
    -0.78
    pher
    -0.77
    graded
    -0.76
    sey
    -0.74
    eal
    -0.73
     paddle
    -0.71
    ebus
    -0.70
    POSITIVE LOGITS
    avorite
    0.76
    çĶŁ
    0.69
    coni
    0.68
    ctr
    0.68
    088
    0.68
    æĺ
    0.67
    000000
    0.67
    UTF
    0.66
    259
    0.66
    ãĤ¼ãĤ¦ãĤ¹
    0.66
    Activations Density 0.045%

    No Known Activations