INDEX

Explanations

phrases related to legal proceedings and announcements

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

 !...

-1.30

 ?...

-1.27

 effe

-1.25

ftu

-1.21

 perfet

-1.21

 increa

-1.19

 indestru

-1.19

 inconce

-1.19

 nece

-1.18

 unwarran

-1.18

POSITIVE LOGITS

 verdict

0.66

 decision

0.64

 whether

0.63

 tomorrow

0.63

 decide

0.61

 decisions

0.60

 externi

0.59

whether

0.59

 deciding

0.58

decision

0.56

Activations Density 0.379%

phrases related to legal proceedings and announcements

No Comments

No Known Activations