INDEX

Explanations

terms related to decoration and ornamentation

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

 Continuum

-0.72

 ब्रेकडाउन

-0.71

Personendaten

-0.70

JNIEnv

-0.69

WarningLevel

-0.68

SNAPSHOT

-0.68

 unknownFields

-0.67

intValue

-0.65

IVEREF

-0.65

Uwe

-0.64

POSITIVE LOGITS

 decoration

2.29

 decorate

2.23

decor

2.20

Decor

2.19

 decorated

2.17

 decorating

2.16

 Decor

2.15

 decorations

2.14

 DECOR

2.10

 decor

2.09

Activations Density 0.084%

terms related to decoration and ornamentation

No Comments

No Known Activations