INDEX

Explanations

strings related to network configuration, particularly those containing "IP" and "ER"

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Fam

-0.58

batik

-0.53

Fam

-0.52

__":

-0.51

gdx

-0.51

lente

-0.50

glEnd

-0.50

gnac

-0.49

fam

-0.49

iense

-0.49

POSITIVE LOGITS

ⓧ

1.06

 فريبيس

0.68

IsContent

0.68

mybatisplus

0.63

 propOrder

0.59

➟

0.57

protoc

0.54

Související

0.53

awtextra

0.52

GraphicsUnit

0.52

Activations Density 24.438%

strings related to network configuration, particularly those containing "IP" and "ER"

No Comments

No Known Activations