INDEX

Explanations

specific proper nouns or significant names in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

“

-0.63

‘

-0.56

 aber

-0.53

des

-0.53

-0.51

uris

-0.50

und

-0.49

ального

-0.47

POSITIVE LOGITS

Efq

1.24

 Monfieur

1.09

 Majefty

1.07

՚

0.98

 myſelf

0.97

ſelf

0.96

 ſind

0.94

 pleaſure

0.93

 Reſ

0.92

 Theſe

0.92

Activations Density 0.258%

specific proper nouns or significant names in the text

No Comments

No Known Activations