INDEX

Explanations

references to death or dead entities

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

URLException

-0.99

kkor

-0.90

깐

-0.90

脚注の使い方

-0.89

styleType

-0.88

 typelib

-0.88

ябре

-0.86

 betreft

-0.85

 esboço

-0.85

RenderAtEndOf

-0.85

POSITIVE LOGITS

 dead

2.33

 Dead

2.22

 DEAD

2.14

Dead

2.13

dead

2.03

DEAD

1.72

死

1.28

 muertos

1.18

 muerto

1.17

死

1.15

Activations Density 0.060%

references to death or dead entities

No Comments

No Known Activations