INDEX

Explanations

numerical values paired with contextual references or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

-0.63

 also

-0.59

 оригіналу

-0.58

-0.56

</b>

-0.55

nością

-0.54

 секунд

-0.53

↵

-0.52

↵↵↵

-0.51

 también

-0.51

POSITIVE LOGITS

abestanden

0.95

Soh

0.84

atorze

0.78

TagMode

0.75

thirty

0.74

 nakalista

0.74

kusen

0.74

ASHINGTON

0.73

venty

0.72

ecute

0.71

Activations Density 1.240%

numerical values paired with contextual references or events

No Comments

No Known Activations