INDEX

Explanations

references to emotions, particularly focusing on positive experiences and their effects

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

 CreateTagHelper

-0.67

BorderStyle

-0.53

 الرياضيه

-0.53

|}{}

-0.52

LOWER

-0.51

 SearchView

-0.51

URG

-0.51

lioz

-0.51

)=-\

-0.50

rawl

-0.50

POSITIVE LOGITS

 positive

0.73

(+)

0.69

 positivo

0.65

 praising

0.64

 Positive

0.64

RTCK

0.62

 positiva

0.62

 praises

0.60

 positif

0.59

 praise

0.59

Activations Density 0.991%

references to emotions, particularly focusing on positive experiences and their effects

No Comments

No Known Activations