INDEX

Explanations

adjectives to describe qualities or states of being, particularly in phrases using "There is" or "There can be."

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

 wherea

-1.16

fta

-1.06

 attemp

-1.04

 maneu

-1.03

 encomp

-1.03

 quitted

-1.01

 purcha

-1.00

 guarante

-1.00

 strick

-0.99

 increa

-0.99

POSITIVE LOGITS

 worauf

0.68

 plenty

0.65

 reason

0.56

 ways

0.55

no

0.53

 nothing

0.53

 sodass

0.53

 womit

0.52

 certain

0.52

cydow

0.52

Activations Density 0.230%

adjectives to describe qualities or states of being, particularly in phrases using "There is" or "There can be."

No Comments

No Known Activations