INDEX

Explanations

instances of specific entertainment or media-related terms, possibly indicating awards or references to content within an entertainment context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 courbe

-0.47

 tán

-0.46

 omgeving

-0.45

 considérable

-0.44

 Strongly

-0.41

com

-0.41

or

-0.41

 signifie

-0.41

 colspan

-0.40

 utara

-0.39

POSITIVE LOGITS

 Houſe

1.13

 myſelf

1.07

ſelf

1.05

 Monfieur

0.98

 itſelf

0.98

 houſe

0.97

 Majefty

0.96

 purpoſe

0.96

 Anſ

0.95

 himſelf

0.94

Activations Density 0.402%

instances of specific entertainment or media-related terms, possibly indicating awards or references to content within an entertainment context

No Comments

No Known Activations