INDEX

Explanations

references to time, particularly durations and specific time periods

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

Follows "of", "has", or "have"

np_acts-logits-general · gemini-2.0-flash

duration of ongoing activities

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

 currently

-0.86

 recently

-0.85

 soon

-0.81

recently

-0.80

currently

-0.79

Recently

-0.77

 yesterday

-0.77

Yesterday

-0.76

 Currently

-0.73

 recentemente

-0.72

POSITIVE LOGITS

 uninterrupted

0.94

 continuously

0.91

 consistently

0.90

 steadily

0.88

 continuous

0.84

 intermittently

0.83

 kontinuier

0.82

Continuous

0.81

 successive

0.78

 consistent

0.77

Activations Density 0.379%

references to time, particularly durations and specific time periods

Follows "of", "has", or "have"

duration of ongoing activities

No Comments

No Known Activations