INDEX

Explanations

phrases indicating a process of change or transformation

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

发表于

-0.64

 Baillargeon

-0.56

だと思います

-0.56

Filmografie

-0.54

 gameOver

-0.52

 Crusoe

-0.52

 equinox

-0.51

nloa

-0.50

 Réponses

-0.50

famille

-0.50

POSITIVE LOGITS

 consultato

0.67

 Theſe

0.65

데

0.63

 thing

0.62

 againſt

0.58

ような

0.58

 것이

0.58

 tartalomajánló

0.57

ContentAsync

0.56

 things

0.55

Activations Density 0.039%

phrases indicating a process of change or transformation

No Comments

No Known Activations