INDEX

Explanations

opinions expressed in a personal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 المعرف

-0.62

ftagPool

-0.60

ArrowToggle

-0.59

 BIBSYS

-0.57

Enllaces

-0.56

 Werden

-0.56

Portale

-0.56

Pois

-0.52

ofas

-0.52

dolu

-0.52

POSITIVE LOGITS

 personally

1.44

 Personally

1.29

 personalmente

1.29

Personally

1.24

 pribadi

1.15

 persönlich

1.04

 personal

1.03

 лично

0.95

personal

0.94

 personlig

0.92

Activations Density 0.142%

opinions expressed in a personal context

No Comments

No Known Activations