INDEX

Explanations

words related to familiarity and interactions with experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 surla

-0.80

 ProtoMessage

-0.79



-0.75

Билгалдахарш

-0.74

rawDesc

-0.73

XmlAccessType

-0.72

kloped

-0.68

">//

-0.66

 ExecuteAsync

-0.62

 noqa

-0.61

POSITIVE LOGITS

 with

2.27

with

1.55

 dengan

1.47

 avec

1.43

 với

1.34

 WITH

1.21

 therewith

1.20

With

1.18

กับ

1.16

 With

1.14

Activations Density 0.436%

words related to familiarity and interactions with experiences

No Comments

No Known Activations