INDEX

Explanations

terms related to alignment and positioning 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 @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 ThemeData

-0.68

Jeografia

-0.66

createClass

-0.63

 Keating

-0.60

 involved

-0.59

---*/

-0.58

 يتيمه

-0.57

 AppBundle

-0.57

💼

-0.56

 FormData

-0.56

POSITIVE LOGITS

 ALIGN

0.82

align

0.78

alignment

0.77

 Align

0.76

 aligns

0.75

 aligning

0.72

Align

0.72

 alignment

0.72

 Alignment

0.71

 parfaite

0.70

Activations Density 0.285%

terms related to alignment and positioning in various contexts

No Comments

No Known Activations