INDEX

Explanations

culinary terms and food-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

didSet

-0.60

phoria

-0.52

BeginContext

-0.52

kháu

-0.51

 kristal

-0.50

Scorecard

-0.49

ภูมิ

-0.49

(!__

-0.49

Bone

-0.49

TRAILING

-0.48

POSITIVE LOGITS

出版年

0.62

 veggies

0.61

 sausage

0.60

 spam

0.57

InstrumentedTest

0.55

 mushrooms

0.54

 Spam

0.53

postmedia

0.53

Spam

0.53

 ground

0.52

Activations Density 0.203%

culinary terms and food-related concepts

No Comments

No Known Activations