INDEX

Explanations

terms related to code or programming concepts

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

king

-1.79

forth

-1.67

leton

-1.66

hof

-1.58

½

-1.57

¹

-1.54

Ŀ

-1.51

↵    ↵

-1.51

↵

-1.51

POSITIVE LOGITS

.'"

1.55

.-

1.50

htra

1.47

 _________________________________

1.41

 where

1.40

 ÂĹ

1.40

.''

1.39

,'"

1.39

'"

1.35

 colors

1.32

Activations Density 0.000%

terms related to code or programming concepts

No Comments

No Known Activations