INDEX

Explanations

terms related to product condition and warranty details

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

migrationBuilder

-0.67

 Relief

-0.63

relief

-0.62

Relief

-0.62

 relief

-0.61

 ujednoznacz

-0.59

 RELIEF

-0.57

➟

-0.56

ására

-0.55

stateProvider

-0.55

POSITIVE LOGITS

+#+#

0.61

AnchorStyles

0.53

 detriment

0.52

pů

0.52

 affect

0.52

 adversely

0.52

 degraded

0.51

 affects

0.51

 negatively

0.51

 alté

0.51

Activations Density 0.687%

terms related to product condition and warranty details

No Comments

No Known Activations

terms related to product condition and warranty details

No Comments

No Known Activations