INDEX

Explanations

references to the name "Peter."

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

 kasarigan

-0.68

 myſelf

-0.67

localctx

-0.65

 Monfieur

-0.65

 itſelf

-0.62

 Shakspeare

-0.61

 Amalgam

-0.59

 pleaſure

-0.58

<caption>

-0.57

Nuorodos

-0.57

POSITIVE LOGITS

borough

0.69

WriteTagHelper

0.62

 CreateTagHelper

0.61

 Peter

0.58

APORE

0.57

WEBPACK

0.56

IsContent

0.51

buro

0.51

 calculées

0.51

 Drucker

0.50

Activations Density 0.052%

references to the name "Peter."

No Comments

No Known Activations