INDEX

Explanations

variations of the word 'adapt' and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zeera

-0.63

VertexArray

-0.61

labelledby

-0.58

serviceWorker

-0.58

usermodel

-0.58

ItemGroup

-0.57

upyter

-0.56

 voice

-0.56

лакти

-0.56

שׁ

-0.55

POSITIVE LOGITS

 Adapt

1.88

 adapted

1.81

 adapts

1.78

 adapt

1.77

 adapting

1.72

 adaptation

1.68

 ADAPT

1.68

adapt

1.66

 Adap

1.65

 adaptations

1.63

Activations Density 0.071%

variations of the word 'adapt' and related concepts

No Comments

No Known Activations