INDEX

Explanations

references to technical and bureaucratic language related to government systems or regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 BrowserModule

-0.66

:][

-0.56

SaveSave

-0.55

istoitu

-0.47

 ۲۰۱

-0.46

xymatrix

-0.46

AutoField

-0.45

riezmann

-0.45

ImageContext

-0.44

ioutil

-0.44

POSITIVE LOGITS

webElementGuid

0.71

tvguidetime

0.61

:✨

0.60

 metaverse

0.57

🫶

0.55

->___

0.52

𝕏

0.50

0.49

 protoimpl

0.49

 Metaverse

0.46

Activations Density 0.180%

references to technical and bureaucratic language related to government systems or regulations

No Comments

No Known Activations