INDEX

Explanations

the word "to" in various contexts, with a significant preference for the preposition "to" used in different phrases and sentences

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

-1.31

fta

-1.31

Juf

-1.26

fup

-1.22

aen

-1.22

 Intere

-1.21

 Mémoires

-1.21

 fays

-1.19

fte

-1.18

 guarante

-1.17

POSITIVE LOGITS

<bos>

0.66

be

0.62

 protect

0.61

 avoid

0.61

 achieve

0.60

 improve

0.60

asts

0.59

 establish

0.58

 expand

0.58

 minimize

0.58

Activations Density 0.235%

the word "to" in various contexts, with a significant preference for the preposition "to" used in different phrases and sentences

No Comments

No Known Activations