INDEX

Explanations

expressions related to user support and recommendations for improvement

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BagConstraints

-0.73

ibatis

-0.58

rrggbb

-0.58

الإنجليزية

-0.57

=>

-0.56

PHONY

-0.55

photobucket

-0.54

 Malk

-0.54

ceto

-0.53

 navbar

-0.52

POSITIVE LOGITS

 bonté

0.59

 ifade

0.58

 noastre

0.52

GenerationType

0.51

 faptul

0.51

 Bertie

0.50

 pleaſure

0.49

 yrity

0.49

protoimpl

0.49

 servici

0.48

Activations Density 0.210%

expressions related to user support and recommendations for improvement

No Comments

No Known Activations