INDEX

Explanations

phrases related to privacy and user information management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ActionButton

-0.52

(&:

-0.50

 pinulongan

-0.49

InstrumentedTest

-0.47

 nawr

-0.46

Laughter

-0.45

towym

-0.43

Ard

-0.43

 elbow

-0.41

 varm

-0.41

POSITIVE LOGITS

ftagPool

0.85

 myſelf

0.72

 ―――――

0.72

 itſelf

0.70

CodedInputStream

0.64

 ་་

0.64

 purpoſe

0.61

 whoſe

0.61

 Majefty

0.61

 Monfieur

0.61

Activations Density 0.128%

phrases related to privacy and user information management

No Comments

No Known Activations