INDEX

Explanations

instances where the word "apparently" is used in text

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

 keramik

-0.67

 klinik

-0.64

 antik

-0.62

 profili

-0.62

 kafe

-0.61

 kapas

-0.61

 silikon

-0.60

 Strukt

-0.60

 mikrofon

-0.58

 majest

-0.57

POSITIVE LOGITS

ագրություններ

0.70

EDEFAULT

0.62

twimg

0.60

 capitaine

0.59

AsUp

0.58

 outputStream

0.57

 bekijken

0.56

Więcej

0.55

 tört

0.55

visející

0.55

Activations Density 0.059%

instances where the word "apparently" is used in text

No Comments

No Known Activations