INDEX

Explanations

interactions involving offering help or showing empathy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

')],

-0.57

newtheorem

-0.57

-->

-0.55

-->

-0.53

spesies

-0.53

壤

-0.52

 Poste

-0.49

cetype

-0.49

läufig

-0.48

ológ

-0.48

POSITIVE LOGITS

ImageContext

0.80

Према

0.69

 المعيارى

0.68

 AspNetCore

0.67

 '\\;'

0.67

AndEndTag

0.65

 stanovnika

0.64

setopt

0.63

ExtendWith

0.62

✭✭

0.61

Activations Density 0.506%

interactions involving offering help or showing empathy

No Comments

No Known Activations