INDEX

Explanations

words found in corporate press releases related to investment, medical research, or pharmaceuticals

oai_token-act-pair · gemini-2.0-flash

unique identifiers or terms

np_token-act-pair-logits · gpt-4o-mini

business contracts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 NSCoder

-0.65

Хьажоргаш

-0.60

 MainAxisSize

-0.53

JAKARTA

-0.52

 bezeichneter

-0.50

 continúas

-0.49

odend

-0.49

Ђ

-0.48

mainen

-0.48

INLINE

-0.48

POSITIVE LOGITS

хьтан

0.66

Manbalar

0.60

 fallu

0.52

tagHelperRunner

0.51

Przypisy

0.51

SharedDtor

0.50

Билгалдахарш

0.49

keyColumn

0.49

 récomp

0.49

 exemplaires

0.49

Activations Density 5.676%

words found in corporate press releases related to investment, medical research, or pharmaceuticals

unique identifiers or terms

business contracts

No Comments

No Known Activations