INDEX

Explanations

Java package imports and related library references.

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Java import statements related to javax and java packages.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

Java import statements, particularly those related to javax packages.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

Code or technical jargon

np_acts-logits-general · gemini-2.0-flash

programming or technical terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 مرئيه

-0.65

новниш

-0.62

 vettoriale

-0.60

gypten

-0.59

 finn

-0.58

tagHelperRunner

-0.53

 Trọng

-0.53

 gyhoeddwyd

-0.53

hoeddwyd

-0.52

 stanovnika

-0.52

POSITIVE LOGITS

 javax

1.44

javax

0.81

קישורים

0.60

runApp

0.59

../../../

0.59

ruptedException

0.59

qualified

0.55

SequentialGroup

0.54

AddWithValue

0.53

SuspendLayout

0.51

Activations Density 0.027%

Java package imports and related library references.

Java import statements related to javax and java packages.

Java import statements, particularly those related to javax packages.

Code or technical jargon

programming or technical terms

No Comments

No Known Activations