INDEX

Explanations

terms related to genetic pathways and classifications

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/2-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.2.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

ľĵ

-3.32

ģ

-3.07

Ĥ¬

-3.03

½

-2.97

Ŀ

-2.93

¯

-2.90

Į

-2.87

¾

-2.84

¿

-2.80

¶

-2.78

POSITIVE LOGITS

merce

1.66

 Galaxy

1.65

ãĥĥãĥĪ

1.57

uminous

1.53

à¸µà¹Ī

1.51

iest

1.42

say

1.41

arant

1.41

iverse

1.40

 Mountains

1.39

Activations Density 2.908%

terms related to genetic pathways and classifications

No Comments

No Known Activations