INDEX

Explanations

phrases related to warnings or advice

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

 parlamento

-0.57

setLayoutParams

-0.53

PageFactory

-0.52

 Siria

-0.51

emmel

-0.51

lccccc

-0.50

 Rumania

-0.50

blurRadius

-0.50

Mâ

-0.49

JpaRepository

-0.49

POSITIVE LOGITS

idać

0.66

 bandai

0.60

 leçon

0.57

 pylab

0.55

 wako

0.54

asteroide

0.52

 underestimate

0.52

 créativité

0.52

 akong

0.50

 épreuve

0.50

Activations Density 0.298%

phrases related to warnings or advice

No Comments

No Known Activations