INDEX

Explanations

occurrences of the data type "Long"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 saites

-1.02

BagLayout

-0.91

GEBURTSDATUM

-0.83

Geplaatst

-0.82

VIAF

-0.82

 clearColor

-0.81

 विश्वसनीयता

-0.77

setArguments

-0.75

 تانيه

-0.75

 تضيفلها

-0.75

POSITIVE LOGITS

 Long

2.60

Long

2.47

LONG

1.39

 LONG

1.14

 Longo

0.99

Short

0.97

Double

0.92

 Short

0.92

Integer

0.85

getLong

0.84

Activations Density 0.083%

occurrences of the data type "Long"

No Comments

No Known Activations