INDEX

Explanations

references to the subject "He" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

saraba

-0.66

ppur

-0.64

 Deta

-0.63

 APPEND

-0.60

 perla

-0.60

 Roundtable

-0.60

 typelib

-0.60

"}")

-0.59

 يتيمه

-0.59

 Staple

-0.59

POSITIVE LOGITS

He

2.62

He

2.16

She

1.46

 Он

1.23

She

1.21

His

1.13

His

1.08

 They

1.08

We

1.02

Him

0.92

Activations Density 0.082%

references to the subject "He" in various contexts

No Comments

No Known Activations