INDEX

Explanations

the word "excuse" or variations of it

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

 Kategor

-0.67

 Kön

-0.64

 keramik

-0.64

 kosme

-0.62

 eorum

-0.61

 silikon

-0.61

 kompati

-0.59

 Frö

-0.59

 kön

-0.59

 meras

-0.58

POSITIVE LOGITS

 excuse

1.31

 excuses

1.19

 Excuse

1.02

excuse

1.01

Excuse

0.95

 excused

0.94

cuses

0.73

躇

0.66

 excus

0.64

 pretext

0.59

Activations Density 0.074%

the word "excuse" or variations of it

No Comments

No Known Activations