INDEX

Explanations

terms indicating limitations or deficiency in knowledge or compliance

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

a small quantity or degree

np_acts-logits-general · gemini-2.0-flash

degree and extent

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 perfons

-0.63

 whofe

-0.50

 HasFactory

-0.49

Na

-0.48

 META

-0.48

autoreleasepool

-0.48

 Chriftian

-0.47

TestBed

-0.47

**/

-0.47

 gyhoeddwyd

-0.46

POSITIVE LOGITS

PullParser

0.67

CppMethod

0.60

ัติ

0.59

 CreateTagHelper

0.57

parsedMessage

0.57

ENED

0.56

 theirs

0.56

ViewFeatures

0.55

dollis

0.54

PerformLayout

0.54

Activations Density 0.497%

terms indicating limitations or deficiency in knowledge or compliance

a small quantity or degree

degree and extent

No Comments

No Known Activations