INDEX

Explanations

instances of the word "own."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 vectorielle

-0.69

 touristique

-0.66

er

-0.65

 vectorielles

-0.65

 énergé

-0.63

 novità

-0.62

 annonce

-0.59

ically

-0.59

 religieuses

-0.59

 lumineux

-0.59

POSITIVE LOGITS

own

2.00

Own

1.74

Own

1.63

OWN

1.61

own

1.52

 eigenen

1.33

 sendiri

1.20

 соб

1.19

OWN

1.18

 eigenes

1.16

Activations Density 0.061%

instances of the word "own."

No Comments

No Known Activations