INDEX

Explanations

instances of phrases that indicate clarity or reference, particularly those that summarize or assert observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 وتسجيلات

-0.87

 Normdatei

-0.70

SOUNDBITE

-0.69

AddTagHelper

-0.65

pecially

-0.65

ärna

-0.64

"/></

-0.62

 ogóle

-0.61

annica

-0.60

ValueStyle

-0.60

POSITIVE LOGITS

0.65

we

0.55

 дописавши

0.53

zg

0.48

之下

0.48

 ApiException

0.47

呢

0.46

0.45

TestFixture

0.44

wegg

0.43

Activations Density 0.228%

instances of phrases that indicate clarity or reference, particularly those that summarize or assert observations

No Comments

No Known Activations