INDEX

Explanations

words related to quantities and their utilization

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

kháu

-0.66

<bos>

-0.62

 AssemblyVersion

-0.61

WebServlet

-0.60

/-/

-0.60

Jeografia

-0.58

tagHelperRunner

-0.58

numerusform

-0.57

Geplaatst

-0.57

hadores

-0.56

POSITIVE LOGITS

 AssemblyTitle

0.57

脚注の使い方

0.57

MathML

0.55

 تضيفلها

0.54

ſelf

0.54

">//

0.53

 itſelf

0.50

︎

0.49

tvguidetime

0.49

étoit

0.48

Activations Density 0.346%

words related to quantities and their utilization

No Comments

No Known Activations