INDEX

Explanations

instances of decision-making or judgment-related phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

IsContent

-0.81

AndroidJUnit

-0.80

 '\\;'

-0.68

featureID

-0.68

 pinulongan

-0.67

 nahilalakip

-0.66

 chi̍t

-0.66

AutoScaleMode

-0.66

utriche

-0.65

GraphicsUnit

-0.63

POSITIVE LOGITS

 dipa

0.45

openg

0.44

翅

0.43

 shutter

0.42

ropa

0.42

 Pública

0.41

eles

0.41

وث

0.41

dra

0.41

точ

0.41

Activations Density 1.882%

instances of decision-making or judgment-related phrases

No Comments

No Known Activations