INDEX

Explanations

phrases that indicate exceptions or unique conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

TagMode

-0.66

 Савезне

-0.63

Chham

-0.59

Personendaten

-0.57

]=>

-0.55

 userSchema

-0.55

 healthiest

-0.54

uxxxx

-0.53

 newBuilder

-0.52

 tailings

-0.52

POSITIVE LOGITS

contentLoaded

0.68

 occasionally

0.61

 exceptions

0.60

 Paglinawan

0.58

 occasional

0.55

例外

0.53

ElementException

0.52

 CanadaChoose

0.52

Occasionally

0.52

 Occasionally

0.50

Activations Density 0.131%

phrases that indicate exceptions or unique conditions

No Comments

No Known Activations