INDEX

Explanations

phrases that indicate long-term perspectives or considerations

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

following "long"

np_acts-logits-general · gemini-2.0-flash

long term

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

plaatst

-0.67

tonode

-0.67

gemaakt

-0.61

 AssemblyTitle

-0.60

queryInterface

-0.60

 hObject

-0.58

PerSecond

-0.57

least

-0.57

ècie

-0.56

 encontram

-0.56

POSITIVE LOGITS

ago

0.98

 term

0.91

 lasting

0.79

lasting

0.79

gggg

0.78

 awaited

0.76

 standing

0.76

ggg

0.75

 overdue

0.74

term

0.73

Activations Density 0.140%

phrases that indicate long-term perspectives or considerations

following "long"

long term

No Comments

No Known Activations