INDEX

Explanations

complex relationships between cause and effect

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Chwiliwch

-0.49

ありました

-0.48

eleste

-0.48

 dulu

-0.47

جیب

-0.46

 scrup

-0.46

光是

-0.46

ficamente

-0.45

kusi

-0.45

SpringRunner

-0.44

POSITIVE LOGITS

 thereby

0.87

 thus

0.75

Datuak

0.74

 hence

0.70

 hivyo

0.68

 therefore

0.68

IndentedString

0.66

 waardoor

0.66

ientôt

0.65

 therefor

0.64

Activations Density 0.553%

complex relationships between cause and effect

No Comments

No Known Activations