INDEX

Explanations

key terms related to significance and implications in research and analysis

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

GEBURTSDATUM

-0.62

 eller

-0.56

 või

-0.56

amzn

-0.55

migrationBuilder

-0.53

 slight

-0.52

 lenker

-0.52

 atau

-0.52

емного

-0.51

úrate

-0.51

POSITIVE LOGITS

 both

1.79

both

1.56

 sowohl

1.45

 especially

1.41

 zowel

1.39

 både

1.34

especially

1.32

Both

1.32

 zarówno

1.31

 particularly

1.30

Activations Density 0.558%

key terms related to significance and implications in research and analysis

No Comments

No Known Activations