INDEX

Explanations

references to the concept of 'inclusion' or 'being included'

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 betweenstory

-0.92

 itſelf

-0.91

RegressionTest

-0.84

 themſelves

-0.81

 myſelf

-0.81

 Theſe

-0.79

 Monfieur

-0.78

AsUp

-0.78

 Jefus

-0.77

 Baillargeon

-0.76

POSITIVE LOGITS

 which

1.15

 including

0.85

 albeit

0.80

which

0.78

 although

0.76

 especially

0.75

 whose

0.74

 cioè

0.73

 cuyo

0.70

 whom

0.70

Activations Density 0.316%

references to the concept of 'inclusion' or 'being included'

No Comments

No Known Activations