INDEX

Explanations

instances of the word "we."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Thon

-0.80

WithIOException

-0.77

 Monfieur

-0.76

Chy

-0.73

 Ueber

-0.70

 Beſ

-0.70

 Salat

-0.70

 frapp

-0.67

 Padang

-0.67

 Paar

-0.66

POSITIVE LOGITS

We

1.52

We

1.50

we

1.49

we

1.22

1.15

WE

1.13

 Weinstein

1.07

 weevil

1.06

 they

1.04

1.03

Activations Density 0.188%

instances of the word "we."

No Comments

No Known Activations