INDEX

Explanations

phrases related to processes involving multiple steps or stages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

classnames

-0.75

 resourceCulture

-0.70

 JpaRepository

-0.67

таратура

-0.64

 disambiguazione

-0.63

Personendaten

-0.63

styleType

-0.62

 jScrollPane

-0.61

 AssemblyTitle

-0.60

POSITIVE LOGITS

 stages

0.90

 processes

0.87

 process

0.85

 Stages

0.75

 lifecycle

0.74

 Processes

0.73

 étape

0.73

环节

0.72

Stages

0.70

 stage

0.69

Activations Density 0.571%

phrases related to processes involving multiple steps or stages

No Comments

No Known Activations