INDEX

Explanations

references to different methods or strategies in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AutoField

-0.58

ChromeDriver

-0.52

tys

-0.52

My

-0.50

kr

-0.49

expandindo

-0.48

-0.47

 PropTypes

-0.47

LETED

-0.46

weta

-0.46

POSITIVE LOGITS

 approaches

1.03

 Approaches

0.98

 Monfieur

0.88

 APPROACH

0.88

 pinulongan

0.86

 Approach

0.85

 itſelf

0.82

 myſelf

0.81

 uſed

0.78

Approach

0.77

Activations Density 0.078%

references to different methods or strategies in various contexts

No Comments

No Known Activations