INDEX

Explanations

phrases that refer to the effects or impacts of various actions or phenomena

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

"impact" or "effect" followed by "of"

np_acts-logits-general · gemini-2.0-flash

effect and impact

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

ChildScrollView

-0.51

 ProtoMessage

-0.43

addGap

-0.42

|<\

-0.40

 giù

-0.39

ernos

-0.39

mbangkan

-0.39

⭒

-0.38

getUid

-0.38

 inoxydable

-0.37

POSITIVE LOGITS

Effect

1.02

effect

1.00

 Effect

1.00

Effects

0.99

 Effects

0.98

 effect

0.93

effects

0.91

 effects

0.90

ffect

0.80

 EFFECTS

0.79

Activations Density 0.208%

phrases that refer to the effects or impacts of various actions or phenomena

"impact" or "effect" followed by "of"

effect and impact

No Comments

No Known Activations