INDEX

Explanations

capitalization patterns typically associated with names or titles

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

ướng

-0.59

})*/

-0.57

undle

-0.56

 Transparency

-0.55

 qualify

-0.55

ණ

-0.53

bibinfo

-0.52

 Doria

-0.52

LECTIONS

-0.52

phors

-0.51

POSITIVE LOGITS

 kasarigan

0.97

ChildScrollView

0.93

PhysRev

0.91

GEBURTSDATUM

0.91

CloseOperation

0.88

+#+#

0.86

MemoryWarning

0.80

 GenerationType

0.80

ThroughAttribute

0.80

WebElementEntity

0.75

Activations Density 0.198%

capitalization patterns typically associated with names or titles

No Comments

No Known Activations