INDEX

Explanations

phrases indicating decision outcomes or important rulings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 Recently

-0.57

Recently

-0.54

 Lately

-0.53

 referenties

-0.53

ępnie

-0.53

Occasionally

-0.53

때

-0.52

 pernah

-0.52

principalColumn

-0.51

гда

-0.51

POSITIVE LOGITS

now

1.27

 Теперь

1.09

Теперь

1.07

 теперь

1.04

now

0.97

これから

0.97

 agora

0.96

 ahora

0.93

Now

0.92

 doré

0.91

Activations Density 0.285%

phrases indicating decision outcomes or important rulings

No Comments

No Known Activations