INDEX

Explanations

categories and references related to living individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ucket

-0.69

 excès

-0.64

 Monfieur

-0.62

PreExecute

-0.61

 itſelf

-0.61

 auffi

-0.61

PickerController

-0.61

 myſelf

-0.59

 tiegħek

-0.58

ticelli

-0.58

POSITIVE LOGITS

 alive

1.27

 active

1.26

 Alive

1.14

Alive

1.10

alive

1.06

 aktif

1.03

active

1.01

 ALIVE

0.94

 Active

0.94

Active

0.92

Activations Density 0.464%

categories and references related to living individuals

No Comments

No Known Activations