INDEX

Explanations

actions and intentions related to defining and elucidating concepts or responsibilities

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

ThemeOverlay

-0.70

 carats

-0.66

EDEFAULT

-0.66

 Houſe

-0.62

Portail

-0.62

 Signalez

-0.61

 morrow

-0.60

 Paglinawan

-0.60

 Савезне

-0.59

>\<^

-0.59

POSITIVE LOGITS

 nakalista

0.61

 sekali

0.57

SourceChecksum

0.55

})));

0.52

he

0.51

for

0.51

DoubleQuotes

0.50

 also

0.50

she

0.49

ंदीखरीदारी

0.47

Activations Density 1.181%

actions and intentions related to defining and elucidating concepts or responsibilities

No Comments

No Known Activations