INDEX

Explanations

code references to an "env" or "environment"

oai_token-act-pair · gemini-2.0-flash

env

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

the

-0.74

-0.73

 news

-0.65

new

-0.64

‘

-0.63

The

-0.59

“

-0.57

 people

-0.57

 following

-0.57

-0.56

POSITIVE LOGITS

 समीक्षक

1.05

 estimés

0.83

ंदीखरीदारी

0.82

цездатний

0.81

 autorytatywna

0.78

MigrationBuilder

0.76

VIAF

0.76

Geplaatst

0.76

 nakalista

0.75

رشف

0.74

Activations Density 1.099%

code references to an "env" or "environment"

env

No Comments

No Known Activations