INDEX

Explanations

content related to solving complex problems or mysteries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

cheiden

-0.63

OGND

-0.62

Expectations

-0.58

NegativeButton

-0.58

antMatchers

-0.57

fromLTRB

-0.57

 Италијани

-0.56

☸

-0.56

ropriate

-0.56

Geplaatst

-0.53

POSITIVE LOGITS

 puzzle

1.80

 puzzles

1.78

 mystery

1.76

 mysteries

1.59

 riddle

1.56

 solve

1.55

 solving

1.54

 solved

1.50

 Puzzles

1.48

 riddles

1.47

Activations Density 0.250%

content related to solving complex problems or mysteries

No Comments

No Known Activations