INDEX

Explanations

instances of the word "which" and its variations within questions and explanations

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

ImageContext

-0.74

 mergeFrom

-0.70

 myſelf

-0.67

Filmografie

-0.64

 ――――

-0.62

IsPostBack

-0.60

RegressionTest

-0.58

 Brahman

-0.58

wieś

-0.58

ſelf

-0.58

POSITIVE LOGITS

 Which

0.83

 WHICH

0.83

Which

0.81

hich

0.74

 luckily

0.74

 vilket

0.74

which

0.73

 thankfully

0.72

 which

0.70

 fortunately

0.69

Activations Density 0.279%

instances of the word "which" and its variations within questions and explanations

No Comments

No Known Activations