INDEX

Explanations

expressions related to personal experiences and empathy

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

Sigue

-0.52

foundation

-0.51

okus

-0.49

キャッチ

-0.47

 styr

-0.47

 signal

-0.47

anho

-0.46

resave

-0.46

เหลือ

-0.46

signal

-0.45

POSITIVE LOGITS

 scenarios

0.67

 المعيارى

0.65

 situations

0.61

 onOptions

0.59

 SEDS

0.59

BeginContext

0.58

RTLD

0.58

 dialami

0.58

 scenario

0.58

 simulate

0.57

Activations Density 0.214%

expressions related to personal experiences and empathy

No Comments

No Known Activations