INDEX

Explanations

references to specific nouns and descriptors

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

"a" followed by a noun/descriptor

np_acts-logits-general · gemini-2.0-flash

a followed by noun

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 tramonto

-0.57

 marge

-0.51

帖最后由

-0.49

 sting

-0.49

expired

-0.48

ổi

-0.48

 bacio

-0.47

PropertyGroup

-0.47

ulaires

-0.47

aryen

-0.47

POSITIVE LOGITS

 مشين

0.96

 which

0.87

which

0.86

cui

0.81

verwijspagina

0.79

hich

0.70

 cual

0.69

rungsseite

0.69

MENAFN

0.68

ThroughAttribute

0.68

Activations Density 0.202%

references to specific nouns and descriptors

"a" followed by a noun/descriptor

a followed by noun

No Comments

No Known Activations