INDEX

Explanations

quantitative measurements and cooking instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

-0.56

եռ

-0.52

 onAnimation

-0.52

[]:

-0.50

exercice

-0.50

ganet

-0.49

ẵn

-0.47

hdashline

-0.47

WaitGroup

-0.46

VIE

-0.46

POSITIVE LOGITS

 tablespoon

1.18

 tablespoons

1.16

 teaspoon

1.10

 tbsp

1.09

 teaspoons

1.07

 spoon

1.04

 spoonful

0.98

spoon

0.97

 cucchiaio

0.94

 Tbsp

0.93

Activations Density 0.292%

quantitative measurements and cooking instructions

No Comments

No Known Activations