INDEX

Explanations

comparative phrases that indicate a preference or contrast between entities

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

 refiere

-0.55

astify

-0.51

shadowOpacity

-0.50

 sendok

-0.49

 있어

-0.49

featureID

-0.47

 tepat

-0.47

하십시오

-0.45

HORE

-0.44

 pères

-0.44

POSITIVE LOGITS

 themſelves

0.81

 myſelf

0.80

 itſelf

0.80

 poffible

0.79

 Jefus

0.78

 himſelf

0.78

ſelves

0.77

 whoſe

0.77

leſs

0.76

 becauſe

0.75

Activations Density 0.459%

comparative phrases that indicate a preference or contrast between entities

No Comments

No Known Activations