INDEX

Explanations

specific statistical or categorical data related to frequency or occurrence

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

 Monfieur

-1.12

 myſelf

-1.12

 Theſe

-1.10

 Jefus

-1.08

 itſelf

-1.04

 bershka

-1.04

Hochspringen

-0.99

 Shakspeare

-0.98

存于互联网档案馆

-0.96

 tartalomajánló

-0.92

POSITIVE LOGITS

0.56

 Meksiku

0.51

0.48

0.46

misa

0.46

car

0.45

0.43

0.42

Activations Density 0.155%

specific statistical or categorical data related to frequency or occurrence

No Comments

No Known Activations