INDEX

Explanations

references to various institutes or organizations associated with educational or professional standards

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

 vertes

-0.48

EndContext

-0.47

 izin

-0.47

 épouse

-0.46

 teneur

-0.46

DESK

-0.46

 sembler

-0.44

 fallu

-0.44

stanley

-0.43

 umid

-0.43

POSITIVE LOGITS

fjspx

0.68

tagHelperRunner

0.62

 صوتيه

0.62

 BoxFit

0.61

tute

0.60

queryInterface

0.60

 ReactDOM

0.60

drawSprites

0.60

互联网档案馆

0.58

Попис

0.58

Activations Density 0.086%

references to various institutes or organizations associated with educational or professional standards

No Comments

No Known Activations