INDEX

Explanations

sentences that involve various forms of the verb "to be" and their negations

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

 disambiguazione

-0.72

########.

-0.63

évaluateur

-0.62

 itself

-0.56

RefNanny

-0.56

 Itself

-0.55

ViewFeatures

-0.54

 '\\;'

-0.53

jahtera

-0.52

</caption>

-0.52

POSITIVE LOGITS

 kidding

0.74

 gonna

0.71

 joking

0.67

 going

0.62

 younger

0.62

 taller

0.60

 seorang

0.59

 doing

0.58

 Púb

0.58

 wearing

0.58

Activations Density 0.308%

sentences that involve various forms of the verb "to be" and their negations

No Comments

No Known Activations