INDEX

Explanations

expressions of possession or experiences indicating the existence of something

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

Auxiliary verbs (has, have, had) followed by past participles

np_acts-logits-general · gemini-2.0-flash

not has/have been

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

]")]

-0.65

ようになる

-0.55

itness

-0.54

りする

-0.52

 vermelhas

-0.50

envolvimento

-0.50

:✨

-0.49

WebServlet

-0.48

 sür

-0.47

setVerticalGroup

-0.47

POSITIVE LOGITS

 been

2.09

been

1.61

 gotten

1.42

 BEEN

1.35

 Been

1.33

got

1.30

Been

1.26

had

1.18

 undergone

1.14

 gone

1.10

Activations Density 0.577%

expressions of possession or experiences indicating the existence of something

Auxiliary verbs (has, have, had) followed by past participles

not has/have been

No Comments

No Known Activations