INDEX

Explanations

verbs related to visibility and actions that can hide or show elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 viewDidLoad

-0.65

 nakalista

-0.61

 createState

-0.57

 anteriore

-0.53

 anzeigen

-0.53

 quinto

-0.52

はじめに

-0.52

 preventivo

-0.50

 Halen

-0.49

↑

-0.48

POSITIVE LOGITS

inout

0.74

InOut

0.70

toggleClass

0.70

 上下

0.68

内外

0.63

 nahilalakip

0.59

oredCriteria

0.58

CompilerServices

0.58

colage

0.57

qrstuvwxyz

0.55

Activations Density 0.481%

verbs related to visibility and actions that can hide or show elements

No Comments

No Known Activations