© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 19744
    Prev
    Next
    INDEX
    Explanations

    words related to organizations or agreements with abbreviations like "EC"

    oai_token-act-pair · gpt-3.5-turbo

    references to the acronym "EC" related to various contexts or organizations

    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
     ç¥ŀ
    -0.71
    pocket
    -0.69
    things
    -0.68
     Revenge
    -0.66
    ãĤ¤ãĥĪ
    -0.66
    yards
    -0.64
     Grimm
    -0.62
     Markus
    -0.62
    down
    -0.62
     Cthulhu
    -0.62
    POSITIVE LOGITS
    EC
    1.10
    oin
    0.99
    ritical
    0.99
    redits
    0.97
    ombat
    0.96
    ycle
    0.94
    ogl
    0.93
    LECT
    0.92
    entric
    0.92
    uador
    0.90
    Activations Density 0.006%

    No Known Activations