INDEX

Explanations

technology-related terms and concepts, particularly regarding communication devices such as beepers, pagers, and online usage patterns

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 utop

-0.99

 potest

-0.94

 notor

-0.94

 solidar

-0.94

 succede

-0.93

 torner

-0.92

 mondeo

-0.90

 sento

-0.90

 ideolog

-0.89

 volete

-0.89

POSITIVE LOGITS

 They

0.75

 However

0.70

 Therefore

0.67

It

0.66

Instrumented

0.64

siyah

0.64

 Though

0.64

 clô

0.64

 accordé

0.64

 considér

0.64

Activations Density 2.239%

technology-related terms and concepts, particularly regarding communication devices such as beepers, pagers, and online usage patterns

No Comments

No Known Activations