INDEX

Explanations

references to different types of lamps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 reaſon

-0.64

 foule

-0.59

 miſ

-0.59

luß

-0.58

 flavor

-0.56

 pleaſure

-0.53

 tasse

-0.53

 honneur

-0.52

 Chaldean

-0.52

 compleanno

-0.51

POSITIVE LOGITS

)}</

0.86

SequentialGroup

0.78

 ModelExpression

0.73

ChildScrollView

0.70

 lamp

0.66

'])){

0.64

yny

0.63

दार

0.62

 BoxFit

0.61

kendo

0.61

Activations Density 0.184%

references to different types of lamps

No Comments

No Known Activations