INDEX

Explanations

words and phrases that connect concepts, especially opposites and alternatives.

oai_token-act-pair · gemini-2.0-flash

conjunctions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Portail

-0.90

Sucesor

-0.89

 resourceCulture

-0.85

sizeCache

-0.79

клопе

-0.78

enumii

-0.78

LookAnd

-0.76

ArgsConstructor

-0.73

RectangleBorder

-0.73

Życiorys

-0.72

POSITIVE LOGITS

itd

0.44

etc

0.43

honneur

0.40

 bancaire

0.40

pap

0.40

0.39

 filmo

0.39

OnInit

0.38

diri

0.38

pro

0.38

Activations Density 11.727%

words and phrases that connect concepts, especially opposites and alternatives.

conjunctions

No Comments

No Known Activations