INDEX

Explanations

entities related to awards and recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 ProtoMessage

-0.82

GenerationType

-0.54

abestanden

-0.53

原始内容存档于

-0.53

+:+

-0.51

ValueStyle

-0.51

"{\

-0.50

Дереккөздер

-0.50

 cref

-0.49

GOTREF

-0.48

POSITIVE LOGITS

 give

2.80

give

2.63

 Give

2.62

Give

2.60

 giving

2.60

 given

2.47

 Giving

2.43

Giving

2.42

 gave

2.41

giv

2.38

Activations Density 0.794%

entities related to awards and recognitions

No Comments

No Known Activations