INDEX

Explanations

specific geographical locations and legal or financial terms related to transactions or actions

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

preceding citations or references

np_acts-logits-general · gemini-2.0-flash

words in lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 ब्रेकडाउन

-0.59

 saites

-0.49

 fön

-0.47

 neumáticos

-0.47

Obrázky

-0.47

 épaules

-0.46

 peinados

-0.46

 تضيفلها

-0.45

 ögon

-0.44

 enfans

-0.43

POSITIVE LOGITS

fromnode

0.73

帖最后由

0.69

InstrumentedTest

0.64

 AssemblyCulture

0.60

ConstraintMaker

0.58

UnusedPrivate

0.54

dropIfExists

0.54

__*/

0.50

 betweenstory

0.50

uxxxx

0.47

Activations Density 0.658%

specific geographical locations and legal or financial terms related to transactions or actions

preceding citations or references

words in lists

No Comments

No Known Activations