INDEX

Explanations

occurrences of the word "data"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 للاسماء

-0.90

expandindo

-0.79

 iLocal

-0.79

RTLE

-0.79

NameInMap

-0.79

withstanding

-0.78

 Convertible

-0.78

SBATCH

-0.78

 Duque

-0.77

@[+][

-0.76

POSITIVE LOGITS

 data

1.68

DATA

1.59

 DATA

1.57

 Data

1.57

data

1.56

Data

1.43

 Daten

1.19

setData

1.17

DataTo

1.17

数据

1.17

Activations Density 0.086%

occurrences of the word "data"

No Comments

No Known Activations