INDEX

Explanations

references to various topics or subjects discussed in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

halb

-0.78

StrictEqual

-0.71

parsedMessage

-0.68

<blockquote>

-0.65

ecore

-0.63

BBBB

-0.62

createServer

-0.61

crose

-0.61

𝑙

-0.60

 superiori

-0.60

POSITIVE LOGITS

 topics

1.80

 TOPIC

1.67

 Topic

1.65

 topic

1.64

 Topics

1.64

Topics

1.63

topics

1.60

Topic

1.52

topic

1.48

TOPIC

1.46

Activations Density 0.065%

references to various topics or subjects discussed in the text

No Comments

No Known Activations