INDEX

Explanations

instances of fairness or unfairness in contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

zkod

-0.46

flüs

-0.45

 autorytatywna

-0.44

orno

-0.43

cham

-0.43

ɜ

-0.43

__()

-0.42

nelson

-0.42

dû

-0.42

 clinical

-0.42

POSITIVE LOGITS

setVerticalGroup

1.08

 Réponses

0.79

WEBPACK

0.66

Personendaten

0.65

MLLoader

0.64

OGND

0.62

createServer

0.60

RegistryLite

0.60

posedge

0.60

 uVar

0.60

Activations Density 0.115%

instances of fairness or unfairness in contexts

No Comments

No Known Activations