INDEX

Explanations

phrases indicating companionship or support

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

start of user input

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

 coming

-0.42

 type

-0.41

 COMING

-0.40

쨌

-0.40

 version

-0.38

 condition

-0.38

 Competition

-0.38

 solution

-0.36

 compensation

-0.36

 hook

-0.36

POSITIVE LOGITS

IsMutable

0.71

RTLR

0.58

featureID

0.57

⤹

0.55

ImageContext

0.52

 disponibilités

0.52

RTLI

0.50

IVEREF

0.49

oredCriteria

0.47

#+#

0.47

Activations Density 0.000%

phrases indicating companionship or support

start of user input

No Comments

No Known Activations