INDEX

Explanations

terms related to alignment and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CoreData

-1.02

Jeografia

-0.88

 NSCoder

-0.88

expandindo

-0.87

ंदीखरीदारी

-0.87

 AppBundle

-0.84

 Fanny

-0.81

-0.80

InjectAttribute

-0.79

 Buxton

-0.79

POSITIVE LOGITS

align

1.57

 align

1.51

 ALIGN

1.36

 Align

1.35

 alignment

1.34

 aligns

1.33

 aligning

1.32

 Alignment

1.29

Align

1.27

alignment

1.27

Activations Density 0.171%

terms related to alignment and its variations in context

No Comments

No Known Activations