INDEX

Explanations

titles or references to works by specific authors, particularly those with recurrent names or themes

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

 itſelf

-0.91

 myſelf

-0.87

 iſt

-0.87

 kaarangay

-0.81

 neceſſ

-0.77

 Diſ

-0.73

 unſ

-0.73

 purpoſe

-0.71

 faſt

-0.70

 ainfi

-0.70

POSITIVE LOGITS

Trama

0.55

TabIndex

0.54

<td>

0.52

CrossRef

0.51

0.50

خرى

0.50

：“……”

0.50

0.49

“

0.49

Activations Density 0.805%

titles or references to works by specific authors, particularly those with recurrent names or themes

No Comments

No Known Activations