INDEX

Explanations

usage of the pronouns "I" and "we"

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.77

EndGlobalSection

-0.86

Autoritní

-0.83

RegressionTest

-0.83

contentLoaded

-0.73

estimable

-0.71

новништво

-0.71

InjectAttribute

-0.69

sizeCache

-0.67

 Савезне

-0.66

POSITIVE LOGITS

 practition

0.95

 maneu

0.93

 impra

0.92

 accla

0.92

 pymysql

0.90

 affor

0.89

 obligé

0.89

 créateur

0.88

 resté

0.87

atguigu

0.87

Activations Density 0.534%

usage of the pronouns "I" and "we"

No Comments

No Known Activations