INDEX

Explanations

words and phrases related to numerical data and calculated differences

oai_token-act-pair · gemini-2.0-flash

terms related to programming or assembly code

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

periods

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

place

-0.58

 place

-0.55

 otherwise

-0.55

рок

-0.50

σο

-0.49

req

-0.46

板

-0.45

yers

-0.45

 away

-0.44

POSITIVE LOGITS

 AssemblyTitle

0.87

 Савезне

0.83

 propOrder

0.81

}}]{

0.80

writeField

0.73

 RIPRODUZIONE

0.73

MigrationBuilder

0.72

Демографія

0.71

 AssemblyCompany

0.70

__*/

0.70

Activations Density 3.952%

words and phrases related to numerical data and calculated differences

terms related to programming or assembly code

periods

No Comments

No Known Activations