INDEX

Explanations

punctuation marks and symbols, particularly parentheses and question marks

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

 ویکی‌پدیا

-0.72

 banc

-0.65

ον

-0.65

 виправивши

-0.65

ilit

-0.65

gany

-0.64

 squee

-0.63

führt

-0.62

Abit

-0.60

 newBuilder

-0.60

POSITIVE LOGITS

（

1.22

（

1.18

：（

1.07

》（

0.99

［

0.97

）（

0.97

｛

0.94

！（

0.92

出版年

0.90

”（

0.89

Activations Density 0.058%

punctuation marks and symbols, particularly parentheses and question marks

No Comments

No Known Activations