INDEX

Explanations

lists or enumerations

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

 متعلقه

-0.77

וויק

-0.69

 otomatig

-0.68

 OFDb

-0.68

Personensuche

-0.64

 समीक्षक

-0.63

Diwedd

-0.61

 للمعارف

-0.60

"}")

-0.60

)++;

-0.59

POSITIVE LOGITS

 étoit

0.54

 culturelles

0.53

 reconnu

0.53

 Pública

0.51

 étrangères

0.51

poved

0.49

 manqué

0.49

zug

0.49

 féd

0.48

 privée

0.48

Activations Density 0.167%

lists or enumerations

No Comments

No Known Activations