INDEX

Explanations

terms related to reverse transcription processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

#+#

-0.63

 يتيمه

-0.62

########.

-0.61

 متعلقه

-0.60

 Taktlose

-0.58

 متحده

-0.58

 beaute

-0.57

abestanden

-0.56

 MenuView

-0.56

fjspx

-0.56

POSITIVE LOGITS

 polarity

0.75

 engineered

0.72

 engineer

0.65

engineered

0.63

engineer

0.63

 engineering

0.59

Personendaten

0.58

 ENGINEER

0.58

engineering

0.57

bootstrapcdn

0.56

Activations Density 0.195%

terms related to reverse transcription processes

No Comments

No Known Activations