INDEX

Explanations

phrases indicating availability and access to services or information

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

chronic exposure and scrutiny

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

 TestBed

-0.54

SequentialGroup

-0.51

قایناق‌لار

-0.47

 unknownFields

-0.45

 kaarangay

-0.44

 Biôgrafia

-0.43

Diwedd

-0.43

 répondit

-0.42

şört

-0.42

̈́

-0.41

POSITIVE LOGITS

__":

0.43

RectangleBorder

0.40

ortal

0.39

 calldata

0.38

amp

0.35

antaine

0.35

ital

0.35

pal

0.35

(~(

0.35

phus

0.34

Activations Density 0.143%

phrases indicating availability and access to services or information

chronic exposure and scrutiny

No Comments

No Known Activations