INDEX

Explanations

expressions that involve comparisons or equality checks

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

java equals comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 pstmt

-0.47

 HomeController

-0.43

 gogh

-0.43

 museum

-0.41

 workforce

-0.41

('/')

-0.41

Donor

-0.40

TagHelper

-0.40

BnF

-0.40

("/{

-0.40

POSITIVE LOGITS

equals

1.30

Equals

0.88

 Equals

0.71

 equals

0.70

EQUALS

0.70

equalsIgnoreCase

0.68

oredCriteria

0.66

equal

0.64

 isEqualToString

0.62

toEqual

0.60

Activations Density 0.003%

expressions that involve comparisons or equality checks

java equals comparison

No Comments

No Known Activations