INDEX

Explanations

words related to physical actions and movements, focusing on a specific activity involving tapping or touching as well as elements hinting at encouragement or gratitude

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 haup

-0.80

 susun

-0.79

 jati

-0.76

 alip

-0.75

umo

-0.75

 jaya

-0.75

 exé

-0.74

 kasa

-0.74

 soggior

-0.74

uhr

-0.72

POSITIVE LOGITS

 thanking

0.77

 greeting

0.75

 congrat

0.75

 greetings

0.72

 thanked

0.69

 congratulate

0.68

 congratulations

0.67

 compliment

0.67

 compliments

0.65

 congratulated

0.65

Activations Density 0.472%

words related to physical actions and movements, focusing on a specific activity involving tapping or touching as well as elements hinting at encouragement or gratitude

No Comments

No Known Activations