INDEX

Explanations

references to victims in various contexts, emphasizing their experiences and identities

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

ⓧ

-0.71

 thiệu

-0.64

DrawerLayout

-0.62

ouage

-0.62

mend

-0.60

 Lawler

-0.60

-0.59

falt

-0.59

 sehat

-0.59

inol

-0.58

POSITIVE LOGITS

 victims

3.27

 victim

3.20

 Victims

2.94

 Victim

2.84

victim

2.81

Victim

2.52

 victimes

2.40

 victime

2.40

 víctimas

2.13

 vítima

2.08

Activations Density 0.084%

references to victims in various contexts, emphasizing their experiences and identities

No Comments

No Known Activations