INDEX

Explanations

references to influential concepts, topics, or entities within a historical and cultural context

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

but

-0.53

).

-0.49

-0.46

--

-0.46

↵↵

-0.44

):

-0.42

 pero

-0.41

↵

-0.41

POSITIVE LOGITS

GraphicsUnit

1.16

CloseOperation

0.97

 ویکی‌پدیای

0.93

 للمعارف

0.89

 nahilalakip

0.87

bootstrapcdn

0.84

rrggbb

0.84

\{\\

0.84

basicConfig

0.79

httphttps

0.78

Activations Density 0.619%

references to influential concepts, topics, or entities within a historical and cultural context

No Comments

No Known Activations