INDEX

Explanations

occurrences of the prefix "Re" in various contexts

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

Lines starting with "Re" or "Re:"

np_acts-logits-general · gemini-2.0-flash

"Re:" emails and "Re-" prefix words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

mergeFrom

-0.57

rz

-0.50

abord

-0.49

}}}

-0.48

":

-0.48

 mesure

-0.47

roy

-0.47

 Proz

-0.46

raz

-0.46

 AssemblyCulture

-0.46

POSITIVE LOGITS

Re

0.76

NOPQRST

0.70

 JpaRepository

0.70

Re

0.69

 مرئيه

0.68

 صوتيه

0.65

 Pyrene

0.65

ArgsConstructor

0.65

Ră

0.62

 Fermi

0.61

Activations Density 0.060%

occurrences of the prefix "Re" in various contexts

Lines starting with "Re" or "Re:"

"Re:" emails and "Re-" prefix words

No Comments

No Known Activations