INDEX

Explanations

terms indicating the retrieval or access of information

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

Autoritní

-0.63

 otomatig

-0.57

("="

-0.49

 Const

-0.45

Const

-0.44

ॉप

-0.44

ếp

-0.44

Mer

-0.43

isPrime

-0.43

 accumulation

-0.43

POSITIVE LOGITS

 Consultado

2.06

 Процитовано

1.96

 Retrieved

1.78

 Abgerufen

1.75

 Accessed

1.57

 abgerufen

1.56

 Besøkt

1.55

原始内容存档于

1.54

consulté

1.51

 Приступљено

1.51

Activations Density 0.066%

terms indicating the retrieval or access of information

No Comments

No Known Activations