INDEX

Explanations

mentions of shifts or changes in various contexts, especially related to attitudes, taxes, and metabolic processes

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

change of direction or movement

np_acts-logits-general · gemini-2.0-flash

direction toward

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sobie

-0.49

sc

-0.48

HttpHeaders

-0.48

Sc

-0.47

rū

-0.45

 kehadiran

-0.44

sc

-0.43

vš

-0.42

 kelahiran

-0.40

 bilo

-0.40

POSITIVE LOGITS

 toward

1.81

 towards

1.78

toward

1.67

towards

1.63

 Toward

1.57

 Towards

1.54

Towards

1.42

Toward

1.39

 away

1.37

 hacia

1.26

Activations Density 0.254%

mentions of shifts or changes in various contexts, especially related to attitudes, taxes, and metabolic processes

change of direction or movement

direction toward

No Comments

No Known Activations