INDEX

Explanations

phrases and terms related to documentation and versioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

principalTable

-0.80

 lccn

-0.53

ComponentModel

-0.52

aturas

-0.48

RenderAtEndOf

-0.48

UnitTesting

-0.47

 isInitialized

-0.46

 ***!

-0.44

actylus

-0.44

TagMode

-0.44

POSITIVE LOGITS

ions

1.29

ion

1.25

ion

1.24

Ion

1.09

 ions

1.07

ION

1.07

IONS

1.06

tion

1.03

Ion

0.99

 tion

0.98

Activations Density 0.383%

phrases and terms related to documentation and versioning

No Comments

No Known Activations