INDEX

Explanations

references to specific organizations and companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Rüyada

-0.61

 Signalez

-0.61

 invokingState

-0.61

ResponseWriter

-0.60

+#+#

-0.59

WebVitals

-0.56

 Biss

-0.56

 Podcast

-0.56

 gemeint

-0.55

POM

-0.54

POSITIVE LOGITS

 estimés

0.78

ageo

0.72

ंदीखरीदारी

0.70

IBM

0.68

ersk

0.61

 Siemens

0.60

 Merck

0.60

 Sony

0.59

 Tinto

0.58

liferay

0.58

Activations Density 0.605%

references to specific organizations and companies

No Comments

No Known Activations

references to specific organizations and companies

No Comments

No Known Activations