INDEX

Explanations

phrases related to searching, investigating, and locating specific entities or objects

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

 thut

-1.46

 effe

-1.44

fte

-1.37

 embra

-1.37

fta

-1.35

aen

-1.34

ftu

-1.31

 nece

-1.28

fep

-1.28

fto

-1.26

POSITIVE LOGITS

find

0.90

 find

0.89

 elusive

0.86

 search

0.85

 found

0.83

 searching

0.81

 searched

0.81

 locate

0.81

search

0.80

 finds

0.80

Activations Density 0.496%

phrases related to searching, investigating, and locating specific entities or objects

No Comments

No Known Activations