INDEX

Explanations

instances of the word "orange" or variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 umani

-0.94

 roulant

-0.90

 avoient

-0.88

 définiti

-0.87

вгений

-0.86

 houſe

-0.84

 Majefty

-0.84

 fourrure

-0.83

 ricor

-0.82

*++

-0.82

POSITIVE LOGITS

Invoice

0.86

qui

0.85

 invoice

0.83

invoice

0.78

 invoices

0.73

 Invoice

0.73

Invoices

0.66

0.61

Fre

0.60

invoices

0.60

Activations Density 0.016%

instances of the word "orange" or variations of it

No Comments

No Known Activations