INDEX

Explanations

conversational phrases indicating uncertainty or opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

extAlignment

-0.90

 الحره

-0.80

出版年

-0.79

principalColumn

-0.77

 otomatig

-0.77

PullParser

-0.76

TagMode

-0.74

LayoutStyle

-0.72

PreferredItem

-0.71

 invokingState

-0.71

POSITIVE LOGITS

){}

0.44

 wouldn

0.44

 pretty

0.44

alım

0.43

ัน

0.43

 дело

0.43

tech

0.41

 aren

0.40

勉

0.40

Activations Density 0.066%

conversational phrases indicating uncertainty or opinion

No Comments

No Known Activations