INDEX

Explanations

references to information and data structures, particularly dictionary-like terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 particular

-1.60

 careful

-1.59

*](#

-1.52

'?"

-1.50

"){

-1.47

 earth

-1.44

ocrine

-1.42

grades

-1.42

 continuous

-1.40

*_

-1.39

POSITIVE LOGITS

ŀ

3.75

Ń

3.52

Ĵ

3.37

£

3.35

ĩ

3.28

Ĳ

3.25

İ

3.24

¥

3.24

ģ

3.19

Ŀ

3.17

Activations Density 0.191%

references to information and data structures, particularly dictionary-like terms

No Comments

No Known Activations