INDEX

Explanations

conjunctions and phrases indicating conditions or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

kháu

-0.49

enciaga

-0.46

的是

-0.41

oda

-0.40

的就是

-0.39

こんにちは

-0.38

vání

-0.38

AddTagHelper

-0.38

SerializedSize

-0.38

chrän

-0.37

POSITIVE LOGITS

 very

1.14

 extremely

1.13

 worth

1.09

extremely

1.03

 VERY

0.97

 capable

0.95

 impossible

0.95

 totally

0.93

 worthy

0.92

 difficult

0.92

Activations Density 0.361%

conjunctions and phrases indicating conditions or relationships

No Comments

No Known Activations