INDEX

Explanations

references to discoveries or results that imply significant conclusions or data analysis

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

that often follow commas

np_acts-logits-general · gemini-2.0-flash

conclusions, results, facts, precursors

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

gulier

-0.58

forName

-0.55

umberland

-0.54

]='\

-0.50

)_/¯

-0.50

{/

-0.49

örgy

-0.47

SystemColors

-0.46

rvats

-0.43

ucket

-0.43

POSITIVE LOGITS

 plus

1.75

plus

1.46

 along

1.35

 PLUS

1.34

along

1.31

Plus

1.27

 плюс

1.23

 Plus

1.22

 ALONG

1.21

 ainsi

1.14

Activations Density 0.603%

references to discoveries or results that imply significant conclusions or data analysis

that often follow commas

conclusions, results, facts, precursors

No Comments

No Known Activations