INDEX

Explanations

references to scientific studies, methodologies, and legal terminology related to evidence and claims

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 popolari

-0.56

ที่สุด

-0.53

èbres

-0.53

 gratuitement

-0.52

uthor

-0.50

pez

-0.49

woordig

-0.49

世界上

-0.48

اطر

-0.48

 excellent

-0.48

POSITIVE LOGITS

 itſelf

1.13

 Monfieur

1.07

 myſelf

1.06

 Anſ

0.97

Efq

0.96

 ―――――

0.92

 pleaſure

0.91

 Jefus

0.88

 himſelf

0.87

IsContent

0.85

Activations Density 1.333%

references to scientific studies, methodologies, and legal terminology related to evidence and claims

No Comments

No Known Activations