INDEX

Explanations

phrases indicating movement or action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

OGND

-0.52

 AssemblyProduct

-0.51

Carriera

-0.50

 createState

-0.49

Viitteet

-0.47

"}";

-0.47

magine

-0.45

wien

-0.45

romolecules

-0.44

oraf

-0.44

POSITIVE LOGITS

 leaving

0.66

 bezeichneter

0.64

 OMITBAD

0.63

RectangleBorder

0.63

 LEAVE

0.62

MethodManager

0.62

 leave

0.60

Leave

0.58

HostException

0.57

 exodus

0.57

Activations Density 0.218%

phrases indicating movement or action

No Comments

No Known Activations