INDEX

Explanations

phrases related to emotional states and personal reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

RenderAtEndOf

-0.81

SourceChecksum

-0.81

 ModelExpression

-0.79

 >=",

-0.76

parsedMessage

-0.72

 parseFrom

-0.71

 autorytatywna

-0.69

 étoit

-0.68

MessageTagHelper

-0.68

 avoient

-0.67

POSITIVE LOGITS

 indeed

0.62

indeed

0.61

XmlAccessorType

0.56

 certainly

0.54

 terhadap

0.49

certainly

0.47

 että

0.47

 whether

0.46

Indeed

0.45

たとえば

0.45

Activations Density 0.552%

phrases related to emotional states and personal reflections

No Comments

No Known Activations