INDEX

Explanations

patterns related to structured data formats or programming constructs

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

webElementXpaths

-0.60

 kaarangay

-0.59

SourceChecksum

-0.56

 protoimpl

-0.52

Hentet

-0.51

 jsPsych

-0.46

новништво

-0.45

LabelTagHelper

-0.45

BuilderFactory

-0.43

CDCl

-0.42

POSITIVE LOGITS

">//

0.65

Przypisy

0.63

</thead>

0.63

 Мексичка

0.62

indrome

0.56

 fallu

0.56

thâu

0.56

LookAnd

0.54

 produisent

0.53

 تانيه

0.52

Activations Density 3.349%

patterns related to structured data formats or programming constructs

No Comments

No Known Activations