INDEX

Explanations

references to personal identity and self-expression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

WebVitals

-0.81

 MainAxisSize

-0.78

 quæ

-0.73

 ویکی‌پدی

-0.73

StoryboardSegue

-0.68

 mennes

-0.67

apnews

-0.67

Literals

-0.66

CWE

-0.66

 tombé

-0.66

POSITIVE LOGITS

IMO

0.57

 IMHO

0.54

IMHO

0.52

 ordinarily

0.48

IMO

0.47

princip

0.47

 >=",

0.46

HEET

0.46

 principally

0.46

 sens

0.45

Activations Density 0.128%

references to personal identity and self-expression

No Comments

No Known Activations