INDEX

Explanations

terms related to environmental impact and health risks

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

positive outcomes or accomplishments

np_acts-logits-general · gemini-2.0-flash

successes and implementation

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

 évent

-0.64

possibly

-0.61

 eventuali

-0.60

Possibly

-0.56

رشف

-0.56

 possibly

-0.56

]")]

-0.56

 OBITUARY

-0.54

 SPOILERS

-0.53

 thôi

-0.53

POSITIVE LOGITS

 successfully

0.92

 achievements

0.86

 successes

0.84

 improved

0.83

 achieved

0.82

 improvements

0.79

 accomplishments

0.78

 successful

0.77

 Successfully

0.75

 recently

0.74

Activations Density 0.197%

terms related to environmental impact and health risks

positive outcomes or accomplishments

successes and implementation

No Comments

No Known Activations