INDEX

Explanations

instances of the word "all" and its variations to indicate inclusivity or universality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 scheme

-0.49

 Jacobsen

-0.48

 device

-0.46

PageRoute

-0.46

 programme

-0.46

 einzu

-0.45

 febru

-0.45

ed

-0.45

 Jacobson

-0.44

hamshire

-0.44

POSITIVE LOGITS

All

1.18

All

1.15

all

1.06

setAll

1.03

ALL

1.03

 Semua

0.94

ALL

0.93

all

0.91

 GetAll

0.84

 semua

0.82

Activations Density 0.259%

instances of the word "all" and its variations to indicate inclusivity or universality

No Comments

No Known Activations