INDEX

Explanations

significant scientific findings and their specific details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 protoimpl

-0.60

 שוליים

-0.59

 autorytatywna

-0.56

 дописавши

-0.54

gbarkeit

-0.52

IntoConstraints

-0.51

 rospy

-0.51

enumii

-0.51

nother

-0.50

awaiter

-0.50

POSITIVE LOGITS

其中的

0.68

 subset

0.64

 مرئيه

0.59

其中

0.58

 Particularly

0.58

Especially

0.56

 spesielt

0.55

setVerticalGroup

0.55

 mortality

0.55

どれ

0.55

Activations Density 0.593%

significant scientific findings and their specific details

No Comments

No Known Activations