INDEX

Explanations

references to programming functions and their usages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

messageInfo

-0.46

 képes

-0.43

われています

-0.42

ともに

-0.39

putExtra

-0.39

 kér

-0.39

 ruota

-0.38

mapreduce

-0.37

ษัท

-0.37

webtoken

-0.36

POSITIVE LOGITS

 uſe

0.70

 iſt

0.69

 ſind

0.67

 purpoſe

0.65

 dafs

0.64

 myſelf

0.63

 ―――――

0.63

 Jefus

0.63

uſ

0.63

 Houſe

0.63

Activations Density 0.667%

references to programming functions and their usages

No Comments

No Known Activations