INDEX

Explanations

instances of the word "then" used to indicate the sequence of events

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

the word "then"

np_acts-logits-general · gemini-2.0-flash

sequencing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 then

-0.97

 alors

-0.95

 entonces

-0.93

alors

-0.82

 allora

-0.82

 damaligen

-0.75

 então

-0.74

Тогда

-0.74

then

-0.70

 Тогда

-0.70

POSITIVE LOGITS

 proceeded

0.99

 proceed

0.91

 comes

0.87

 they

0.85

 again

0.83

 followed

0.83

we

0.82

 proceeds

0.81

 there

0.80

 secondly

0.75

Activations Density 0.185%

instances of the word "then" used to indicate the sequence of events

the word "then"

sequencing

No Comments

No Known Activations