INDEX

Explanations

words and phrases indicating contextually important entities or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

,=

-0.51

={()

-0.50

endregion

-0.48

 recognised

-0.47

baric

-0.46

ografija

-0.46

Compli

-0.46

 оригіналу

-0.46

esModule

-0.45

ĝ

-0.45

POSITIVE LOGITS

 المعيارى

0.68

SL

0.68

 onData

0.67

SL

0.65

sl

0.64

 saites

0.60

Sl

0.59

sl

0.57

 chịu

0.56

Sl

0.55

Activations Density 2.309%

words and phrases indicating contextually important entities or subjects

No Comments

No Known Activations