INDEX

Explanations

references to forward-looking statements and legal disclaimers

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

Diwedd

-0.57

Clik

-0.49

Tabbed

-0.48

alate

-0.47

 catholique

-0.47

ิด

-0.46

sharing

-0.45

dź

-0.45

 preuves

-0.44

داران

-0.44

POSITIVE LOGITS

item

1.90

 item

1.75

 Item

1.59

Item

1.50

 ITEM

1.47

items

1.39

 items

1.33

 Items

1.33

ITEM

1.32

ItemSelected

1.21

Activations Density 0.033%

references to forward-looking statements and legal disclaimers

No Comments

No Known Activations