INDEX

Explanations

time-related phrases or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ไว้

-0.50

 romain

-0.49

 findById

-0.45

ocu

-0.44

ïe

-0.43

zeb

-0.43

ziesz

-0.43

brainly

-0.43

🏿

-0.43

 Haye

-0.42

POSITIVE LOGITS

SequentialGroup

0.81

 propOrder

0.79

تقاوى

0.78

 sumpay

0.77

 Roskov

0.72

 виправивши

0.70

ंदीखरीदारी

0.69

UnsafeEnabled

0.68

 betweenstory

0.67

Sucesor

0.65

Activations Density 0.243%

time-related phrases or references

No Comments

No Known Activations