INDEX

Explanations

mentions of names and titles

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

 utafitiHapana

-0.74

awtextra

-0.68

 contextLoads

-0.65

contentLoaded

-0.65

 Egli

-0.64

findpost

-0.64

 للمعارف

-0.64

 <=",

-0.63

GraphicsUnit

-0.63

ecake

-0.62

POSITIVE LOGITS

 name

1.50

 title

1.31

 names

1.30

 Name

1.30

 NAME

1.20

name

1.17

名字

1.13

 nickname

1.13

 Names

1.13

 naming

1.13

Activations Density 0.189%

mentions of names and titles

No Comments

No Known Activations