INDEX

Explanations

measures and quantities typically used in cooking or ingredients

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Affiliations

-0.70

 beginnetje

-0.67

saraba

-0.66

 demografica

-0.64

ſelves

-0.62

ſelf

-0.60

 odkazy

-0.59

VIE

-0.59

 Grot

-0.58

 insuffisamment

-0.58

POSITIVE LOGITS

 tablespoon

1.20

 tablespoons

1.18

 teaspoon

1.12

 cucchiaio

1.10

 teaspoons

1.07

 spoon

1.04

 tbsp

1.03

 spoonful

1.03

spoon

0.98

Spoon

0.97

Activations Density 0.121%

measures and quantities typically used in cooking or ingredients

No Comments

No Known Activations