INDEX

Explanations

phrases that indicate outcomes or consequences

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

"result" or "resulting"

np_acts-logits-general · gemini-2.0-flash

resulting in or from

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

-0.87

Efq

-0.76

ReusableCell

-0.74

 endian

-0.71

 NDEBUG

-0.66

 وتسجيلات

-0.61

 Monfieur

-0.61

puerta

-0.60

 MainAxisSize

-0.60

corazón

-0.60

POSITIVE LOGITS

 resulting

0.86

 resulted

0.78

 result

0.73

 résult

0.70

 RESULT

0.68

 Result

0.66

 daraus

0.64

resulting

0.64

 resultant

0.64

 results

0.63

Activations Density 0.170%

phrases that indicate outcomes or consequences

"result" or "resulting"

resulting in or from

No Comments

No Known Activations