INDEX

Explanations

instances of demonstrative pronouns indicating specificity or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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



-0.94

 betweenstory

-0.58

 guineas

-0.54

 CreateTagHelper

-0.52

 olarak

-0.50

 ModelExpression

-0.49

 destinies

-0.48

hidupan

-0.48

 gambe

-0.48

 canoes

-0.47

POSITIVE LOGITS

 particular

1.39

particular

1.23

Particular

0.95

 kind

0.94

 same

0.93

 latter

0.91

 Particular

0.88

 type

0.81

PARTIC

0.79

 particolare

0.78

Activations Density 0.383%

instances of demonstrative pronouns indicating specificity or emphasis

No Comments

No Known Activations