INDEX

Explanations

terms related to alignment and positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 CoreData

-0.98

ंदीखरीदारी

-0.95

expandindo

-0.85

Jeografia

-0.84

Personensuche

-0.83

 NSCoder

-0.80

 AppBundle

-0.79

 "..\..\..\

-0.79

حياته

-0.77

期刊论文

-0.76

POSITIVE LOGITS

align

1.65

 align

1.56

 Align

1.47

 ALIGN

1.41

 aligns

1.41

 alignment

1.39

 aligning

1.38

Align

1.36

 Alignment

1.35

 alignments

1.34

Activations Density 0.120%

terms related to alignment and positioning

No Comments

No Known Activations