INDEX

Explanations

phrases indicating obligations or expectations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

исленность

-0.68

jstor

-0.66

 Walkover

-0.66

ukone

-0.65

MemoryWarning

-0.65

isticated

-0.64

 незавершена

-0.61

raits

-0.61

ingly

-0.60

Personendaten

-0.60

POSITIVE LOGITS

be

0.70

 StringField

0.59

 CreateTagHelper

0.55

 bear

0.54

gatsby

0.53

/*:

0.53

do

0.53

go

0.53

be

0.53

 hide

0.52

Activations Density 0.167%

phrases indicating obligations or expectations

No Comments

No Known Activations