INDEX

Explanations

evaluations of effectiveness and usability in various 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

 createState

-0.58

étique

-0.50

\{\\

-0.49

ernalia

-0.47

IENTE

-0.47

 prés

-0.44

colage

-0.44

ýl

-0.44

 Total

-0.43

 OnInit

-0.43

POSITIVE LOGITS

它们

0.80

 kasarigan

0.72

 Them

0.70

expandindo

0.70

 theyre

0.69

它們

0.68

 EconPapers

0.67

These

0.66

They

0.66

 These

0.64

Activations Density 0.400%

evaluations of effectiveness and usability in various contexts

No Comments

No Known Activations