INDEX

Explanations

statistical evidence and observations related to research findings

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

Follows "observe" or "observed"

np_acts-logits-general · gemini-2.0-flash

observe findings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

rsiniz

-0.47

do

-0.44

 nervosa

-0.43

 gravedad

-0.42

 offerta

-0.42

lieb

-0.41

 necessariamente

-0.41

 amends

-0.41

HasIndex

-0.41

 tomography

-0.41

POSITIVE LOGITS

 significant

0.92

+#+

0.86

ificant

0.76

 increased

0.73

 considerable

0.73

significant

0.72

 apparent

0.70

 slight

0.69

canestro

0.69

 signs

0.69

Activations Density 0.917%

statistical evidence and observations related to research findings

Follows "observe" or "observed"

observe findings

No Comments

No Known Activations