INDEX

Explanations

words related to limitations or boundaries

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

لينكات

-0.57

ValueGeneration

-0.52

URERS

-0.50

ANTAGES

-0.49

leyeb

-0.49

 disambiguazione

-0.48

ensement

-0.48

URATION

-0.47

providedIn

-0.46

 fået

-0.46

POSITIVE LOGITS

li

1.09

Li

1.07

Li

1.03

LI

0.96

 quoique

0.94

 Lith

0.92

LIP

0.89

 Lilli

0.85

Lia

0.82

Lio

0.82

Activations Density 0.145%

words related to limitations or boundaries

No Comments

No Known Activations