INDEX

Explanations

phrases related to social interactions or conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.57

en

-0.57

-0.53

-0.48

‘

-0.47

<sup>

-0.44

“

-0.43

Dor

-0.43

-0.42

 inter

-0.42

POSITIVE LOGITS

 myſelf

1.31

 itſelf

1.20

ChildScrollView

1.15

IsContent

1.14

 initComponents

1.12

makeConstraints

1.11

 uſed

1.11

Efq

1.10

 AssemblyCulture

1.08

Autoritní

1.07

Activations Density 0.312%

phrases related to social interactions or conversations

No Comments

No Known Activations