INDEX

Explanations

conditional phrases and scenarios indicating potential failures or issues

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

Following "not," "even," or "or" followed by a negative consequence

np_acts-logits-general · gemini-2.0-flash

not completely

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

OGND

-0.44

"["

-0.43

стри

-0.43

тся

-0.43

iene

-0.43

 Италијани

-0.42

'['

-0.41

合理的

-0.40

 uppdater

-0.40

ook

-0.40

POSITIVE LOGITS

 outright

1.39

 completely

1.19

 entirely

1.13

 downright

1.10

 Completely

1.05

 totally

1.04

completely

1.01

 altogether

0.97

 gänzlich

0.95

Completely

0.93

Activations Density 0.530%

conditional phrases and scenarios indicating potential failures or issues

Following "not," "even," or "or" followed by a negative consequence

not completely

No Comments

No Known Activations