INDEX

Explanations

phrases related to effects and influences in various contexts

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

interopRequire

-0.51

 atend

-0.50

gewin

-0.47

cinfo

-0.47

飯

-0.43

erialized

-0.43

 Routed

-0.42

हाय

-0.42

่ง

-0.41

éril

-0.41

POSITIVE LOGITS

 ModelExpression

0.98

IndentedString

0.91

сылкі

0.83

 влияние

0.81

wiſe

0.79

 Paglinawan

0.79

 Италијани

0.79

%)$

0.73

byes

0.72

 Role

0.72

Activations Density 0.332%

phrases related to effects and influences in various contexts

No Comments

No Known Activations