INDEX

Explanations

emotional states and reactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

+#+#

-0.64

ThroughAttribute

-0.61

 understatement

-0.60

RequestMapping

-0.60

ंदीखरीदारी

-0.59

<bos>

-0.59

 Obre

-0.55

apollo

-0.55

mphony

-0.55

cuerdo

-0.53

POSITIVE LOGITS

 memoized

0.56

 becomes

0.56

ListItemIcon

0.55

núť

0.54

 become

0.53

 becoming

0.53

 nanti

0.52

webElementXpaths

0.52

Morfo

0.51

osy

0.51

Activations Density 0.130%

emotional states and reactions

No Comments

No Known Activations