INDEX

Explanations

phrases or statements that provide specifications or parameters in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

↵↵

-0.60

 peggio

-0.51

<h1>

-0.49

<bos>

-0.48

<h2>

-0.48

 outnumbered

-0.47

 triplets

-0.47

Попис

-0.46

 createState

-0.46

POSITIVE LOGITS

 للاسماء

0.72

SequentialGroup

0.68

 الحره

0.66

 minOccurs

0.66

 ligiloj

0.63

出版年

0.61

 ProtoMessage

0.60

 BoxFit

0.59

MemoryWarning

0.58

Hochspringen

0.57

Activations Density 0.024%

phrases or statements that provide specifications or parameters in a technical context

No Comments

No Known Activations