INDEX

Explanations

active verbs related to making, assessing, and creating processes or changes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.49

ki

-0.48

 maat

-0.47

um

-0.46

ki

-0.46

[]>(

-0.43

PLUS

-0.42

ukin

-0.42

„

-0.42

さまでした

-0.41

POSITIVE LOGITS

存于互联网档案馆

0.87

 CreateTagHelper

0.86

ChildScrollView

0.82

 contextLoads

0.82

 AssemblyTitle

0.82

principalColumn

0.79

CROSSTALK

0.79

 itſelf

0.78

makeText

0.78

astify

0.78

Activations Density 0.695%

active verbs related to making, assessing, and creating processes or changes

No Comments

No Known Activations