INDEX

Explanations

numerical values and identifiers associated with various measurements or categories

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

Hexadecimal representations and numbers

np_acts-logits-general · gemini-2.0-flash

numbers and short sequences

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

 insuffisamment

-0.58

migrationBuilder

-0.58

 estekak

-0.58

SourceChecksum

-0.57

 useHistory

-0.54

 گزارش

-0.52

 aDecoder

-0.49

yargs

-0.48

yet

-0.48

userdetails

-0.48

POSITIVE LOGITS

ogos

0.54

hobia

0.54

Mid

0.54

 antichi

0.53

 waard

0.53

"}"

0.52

ụp

0.52

出版年

0.52

 tiroirs

0.52

InputTagHelper

0.52

Activations Density 0.036%

numerical values and identifiers associated with various measurements or categories

Hexadecimal representations and numbers

numbers and short sequences

No Comments

No Known Activations