INDEX

Explanations

negative expressions indicating denial or absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 poveznice

-0.55

Younger

-0.52

 evolucion

-0.52

 Younger

-0.52

 âgé

-0.51

 aquilo

-0.51

 auxquelles

-0.51

 Cæsar

-0.49

 respectivement

-0.48

which

-0.48

POSITIVE LOGITS

no

1.05

LEncoder

0.83

UIControlState

0.83

No

0.77

igno

0.77

NUMX

0.77

₂+

0.73

NO

0.71

 هیچ

0.71

 NavController

0.71

Activations Density 0.152%

negative expressions indicating denial or absence

No Comments

No Known Activations