INDEX

Explanations

words related to events and event handling in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Efq

-1.52

 purpoſe

-1.46

 Anſ

-1.45

 themſelves

-1.43

 itſelf

-1.38

 himſelf

-1.29

 Jefus

-1.28

 myſelf

-1.28

 Theſe

-1.27

 raiſ

-1.27

POSITIVE LOGITS

event

1.75

 event

1.29

evt

0.84

evt

0.83

↵↵

0.73

EVENT

0.70

0.68

0.66

 events

0.62

ho

0.62

Activations Density 0.064%

words related to events and event handling in programming contexts

No Comments

No Known Activations