INDEX

Explanations

references to rumors and their validity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Diweddarwch

-0.80

OpenHelper

-0.55

wegg

-0.50

 Dames

-0.48

hitheater

-0.48

 Expressway

-0.48

 choice

-0.47

remadura

-0.47

creativecommons

-0.46

hskip

-0.46

POSITIVE LOGITS

 rumors

1.41

 rumours

1.37

 rumour

1.36

 rumor

1.33

 Rumors

1.21

Rumors

1.13

 allegations

1.06

 rumores

1.06

 allegation

1.02

 speculation

1.00

Activations Density 0.252%

references to rumors and their validity

No Comments

No Known Activations