INDEX

Explanations

the word "compared" and variations of its usage in different contexts

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 Ferry

-0.64

-0.62

-0.59

انيف

-0.57

ífica

-0.56

ならない

-0.54

sterious

-0.54

Rite

-0.53

iffy

-0.53

ي

-0.53

POSITIVE LOGITS

Compared

1.05

 Compared

1.05

 compared

1.04

compared

1.01

 rispetto

0.88

 Мексичка

0.85

AddTagHelper

0.75

 verg

0.74

Vgl

0.74

PLAC

0.73

Activations Density 0.025%

the word "compared" and variations of its usage in different contexts

No Comments

No Known Activations