INDEX

Explanations

numerical data and formatting patterns within the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UnusedPrivate

-0.70

))[

-0.66

انيف

-0.63

médiaire

-0.61

 سكانية

-0.61

SequentialGroup

-0.60

addCriterion

-0.60

Jereo

-0.59

styleable

-0.58

antMatchers

-0.58

POSITIVE LOGITS

 useDispatch

0.83

 yourself

0.72

 himself

0.64

 herself

0.64

yourself

0.61

Билгалдахарш

0.55

 oneself

0.53

 استنادى

0.53

ionage

0.52

 Besøkt

0.52

Activations Density 0.190%

numerical data and formatting patterns within the text

No Comments

No Known Activations