INDEX

Explanations

conditional phrases indicating uncertainty or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ollectionView

-1.07

ECA

-0.92

SBATCH

-0.92

quelize

-0.92

IFA

-0.87

ergies

-0.86

 Breen

-0.85

CardHeader

-0.84

 Lipa

-0.83

 Placer

-0.83

POSITIVE LOGITS

 might

1.23

 MIGHT

1.20

 Might

1.15

might

1.14

Might

1.08

 would

1.04

 WOULD

0.94

 could

0.85

 Would

0.84

Would

0.83

Activations Density 0.059%

conditional phrases indicating uncertainty or possibility

No Comments

No Known Activations