INDEX

Explanations

terms related to ongoing or current processes, particularly in clinical or investigative contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

csname

-0.63

sequelize

-0.63

 useSelector

-0.62

webdriver

-0.60

DispatchToProps

-0.59



-0.59

PositiveButton

-0.58

 kotlin

-0.58

 defStyle

-0.58

 esperienze

-0.57

POSITIVE LOGITS

 ongoing

1.32

ongoing

1.29

 Ongoing

1.21

Ongoing

1.13

pending

0.94

 pending

0.93

 underway

0.93

ngoing

0.93

PENDING

0.91

 upcoming

0.90

Activations Density 0.139%

terms related to ongoing or current processes, particularly in clinical or investigative contexts

No Comments

No Known Activations