INDEX

Explanations

directive phrases that indicate showing or pointing something out

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

"@

-0.45

 overras

-0.43

 either

-0.39

 Either

-0.38

ENV

-0.37

get

-0.37

 ändå

-0.36

פט

-0.36

 hagy

-0.35

oquia

-0.35

POSITIVE LOGITS

InjectAttribute

0.96

MethodManager

0.94

 CreateTagHelper

0.94

 estimés

0.91

DockStyle

0.90

 linkovi

0.86

uxxxx

0.84

 initComponents

0.83

 saites

0.79

 विश्वसनीयता

0.79

Activations Density 0.155%

directive phrases that indicate showing or pointing something out

No Comments

No Known Activations