INDEX

Explanations

expressions of comparison or similarity

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

 Exactos

-0.78

]-'

-0.73

 تعدى

-0.72

 '\\;'

-0.72

 Majefty

-0.65

Autoritní

-0.64

Билгалдахарш

-0.63

 theſe

-0.62

 Monfieur

-0.61

\{\\

-0.60

POSITIVE LOGITS

Like

0.52

 Like

0.49

OrDefault

0.49

 nargin

0.46

nativeElement

0.45

SizeF

0.45

 edição

0.45

 szá

0.44

aller

0.44

 Hach

0.44

Activations Density 0.099%

expressions of comparison or similarity

No Comments

No Known Activations