INDEX

Explanations

references to healthcare and medical terminology

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

experiencing transient experimental complications

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 kasarigan

-0.69

SharedDtor

-0.60

RTDA

-0.56

=$?

-0.56

jsxFileName

-0.55

sizeCache

-0.54

ngrx

-0.54

 estimés

-0.54

 giggled

-0.53

-0.52

POSITIVE LOGITS

 civilización

0.44

 außerdem

0.35

 inoltre

0.35

woor

0.33

 utilización

0.32

 supervivencia

0.32

 zudem

0.32

 infatti

0.30

gapan

0.30

 therefore

0.29

Activations Density 0.117%

references to healthcare and medical terminology

experiencing transient experimental complications

No Comments

No Known Activations