INDEX

Explanations

code-related syntax and structure, particularly in database connection configurations

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

database connection parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

AndEndTag

-0.60

featureID

-0.58

codile

-0.57

énario

-0.56

contentLoaded

-0.50

 kaarangay

-0.50

ſelf

-0.50

 unſ

-0.49

 itſelf

-0.47

 étoit

-0.46

POSITIVE LOGITS

SequentialGroup

0.49

principalColumn

0.46

 meisje

0.36

HasIndex

0.36

 operator

0.33

QMetaType

0.32

awtextra

0.31

WindowConstants

0.31

antía

0.30

 grantee

0.30

Activations Density 0.004%

code-related syntax and structure, particularly in database connection configurations

database connection parameters

No Comments

No Known Activations