INDEX

Explanations

references to military service and ranks

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

operational

-0.58

 NUKAT

-0.58

 operational

-0.57

rijfs

-0.56

 Leal

-0.54

ValueStyle

-0.53

krishnan

-0.53

eachtet

-0.53

enerated

-0.52

NLA

-0.51

POSITIVE LOGITS

 MongoClient

0.56

 برانيه

0.56

RenderAtEndOf

0.56

kese

0.50

 internetowa

0.49

 OpenAPI

0.48

 serve

0.45

serve

0.45

Kjelder

0.44

DotNetBar

0.43

Activations Density 0.210%

references to military service and ranks

No Comments

No Known Activations