INDEX

Explanations

negative reviews or criticisms of service quality in dining contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Picchu

-0.58

anyeol

-0.55

 SqlParameter

-0.53

oblastoma

-0.52

 lifelong

-0.52

 pears

-0.52

brania

-0.52

 Nuts

-0.51

每年

-0.51

enumi

-0.51

POSITIVE LOGITS

 dining

0.66

 waiter

0.61

scriptcase

0.61

 staff

0.61

 обслужи

0.61

 waitress

0.60

staff

0.59

PRNewswire

0.58

 menus

0.57

 seating

0.57

Activations Density 0.074%

negative reviews or criticisms of service quality in dining contexts

No Comments

No Known Activations