INDEX

Explanations

technical and scientific terms related to measurement and methodology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

".

-1.58

"])

-1.50

"))

-1.47

")){

-1.45

)");

-1.41

.";

-1.41

'},

-1.39

"):

-1.37

.")

-1.33

'))

-1.33

POSITIVE LOGITS

0.58

0.57

//

0.51

et

0.49

.,

0.48

0.46

0.44

−

0.44

Activations Density 1.460%

technical and scientific terms related to measurement and methodology

No Comments

No Known Activations