INDEX

Explanations

references to specific places, events, or entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Datuak

-0.79

 myſelf

-0.73

 ujednoznacz

-0.73

 pleaſure

-0.69

 raiſ

-0.69

 itſelf

-0.68

曖昧さ回避

-0.68

DebuggerNonUser

-0.67

 himſelf

-0.66

 themſelves

-0.65

POSITIVE LOGITS

 deep

0.55

 amid

0.49

Amid

0.48

 pylint

0.48

?>

0.47

ollectionView

0.46

 amidst

0.46

BufferException

0.46

argout

0.45

ïse

0.44

Activations Density 0.271%

references to specific places, events, or entities

No Comments

No Known Activations