INDEX

Explanations

references to academic or research citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 myſelf

-0.98

tagHelperRunner

-0.94

 Jefus

-0.92

 itſelf

-0.91

 initComponents

-0.90

 occaf

-0.89

 Reſ

-0.89

 pleaſure

-0.89

 ſche

-0.88

 becauſe

-0.87

POSITIVE LOGITS

<th>

0.50

↵

0.49

</i>

0.43

<b>

0.42

ربعة

0.42

0.41

<td>

0.41

بوابة

0.40

•

0.40

 living

0.40

Activations Density 0.005%

references to academic or research citations

No Comments

No Known Activations