INDEX

Explanations

terms related to conflicts and confounding factors in research

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

openzeppelin

-0.81

reactivex

-0.80

abestanden

-0.74

antMatchers

-0.71

Aye

-0.66

 Spade

-0.66

/******/

-0.65

 Peoria

-0.65

RegistryLite

-0.63

 rute

-0.63

POSITIVE LOGITS

conf

3.13

Conf

3.04

 Conf

2.99

 conf

2.94

 CONF

2.46

CONF

2.30

 Confessions

1.60

 confessions

1.58

 Konf

1.51

 confession

1.48

Activations Density 0.059%

terms related to conflicts and confounding factors in research

No Comments

No Known Activations