INDEX

Explanations

references to the word "do" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

出版年

-0.79

__':

-0.74

ValueStyle

-0.74

')):

-0.73

 Pyrr

-0.70

 onResponse

-0.70

MessageState

-0.69

########.

-0.68

 Ender

-0.66

MOQ

-0.66

POSITIVE LOGITS

del

1.08

the

1.05

Le

0.96

 το

0.94

 τον

0.92

 στο

0.90

du

0.88

el

0.87

 του

0.85

le

0.83

Activations Density 0.074%

references to the word "do" and its variations in different contexts

No Comments

No Known Activations