INDEX

Explanations

references to published works or studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-0.90

makeConstraints

-0.83

 ſeveral

-0.82

Efq

-0.81

 itſelf

-0.80

GenerationType

-0.80

 ſtill

-0.79

 Diſ

-0.79

 faſt

-0.78

 uſed

-0.75

POSITIVE LOGITS

ad

0.67

PositiveButton

0.67

 tech

0.64

 claim

0.63

mod

0.61

 capacity

0.60

 super

0.58

googleapis

0.58

Claim

0.54

 Claim

0.53

Activations Density 0.158%

references to published works or studies

No Comments

No Known Activations