INDEX

Explanations

technical jargon related to programming and computing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Савезне

-0.68

IFORNIA

-0.66

iſt

-0.64

 beginnetje

-0.64

IndentedString

-0.63

hésite

-0.62

 >=",

-0.62

]<<

-0.60

bibinfo

-0.60

 واب

-0.59

POSITIVE LOGITS

PositiveButton

0.60

asteroide

0.60

 remercier

0.59

AutoField

0.57

ImageField

0.52

literals

0.50

Atoi

0.49

mergeFrom

0.49

ContextHolder

0.49

FilterChain

0.49

Activations Density 0.328%

technical jargon related to programming and computing

No Comments

No Known Activations