INDEX

Explanations

phrases that indicate evidence or inferences based on observations or results

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

AndEndTag

-0.68

 fubject

-0.60

 Cæsar

-0.55

 Carthage

-0.54

 hoor

-0.51

astanza

-0.51

 poland

-0.51

 purpoſe

-0.50

 ſtate

-0.50

 Eury

-0.50

POSITIVE LOGITS

 thus

0.66

 thereby

0.63

 незавершена

0.58

 hence

0.58

Билгалдахарш

0.57

Šaltiniai

0.57

 somit

0.56

 Thus

0.56

новниш

0.56

tagHelperRunner

0.55

Activations Density 0.433%

phrases that indicate evidence or inferences based on observations or results

No Comments

No Known Activations