INDEX

Explanations

the word "those" in various contexts

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

the demonstrative 'those'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bcryptjs

-0.51

VIAF

-0.51

 setColor

-0.50

inheit

-0.49

GEBURTSDATUM

-0.49

 isIn

-0.48

Bir

-0.47

culus

-0.46

simulator

-0.45

서는

-0.45

POSITIVE LOGITS

 those

1.13

 THOSE

1.06

Those

1.02

 Those

0.99

those

0.95

那些

0.80

queles

0.76

 these

0.69

 ceux

0.68

 aquellos

0.68

Activations Density 0.031%

the word "those" in various contexts

the demonstrative 'those'

No Comments

No Known Activations