INDEX

Explanations

notes and important information within 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 @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Portale

-0.70

addPreferredGap

-0.69

tificates

-0.63

pius

-0.61

@}

-0.61

 estekak

-0.61

 endblock

-0.61

complexType

-0.60

WaitGroup

-0.59

 Schell

-0.57

POSITIVE LOGITS

 Note

1.09

 note

1.06

Note

1.05

 NOTE

1.03

NOTE

0.96

note

0.84

 caution

0.73

 caveat

0.72

WARNING

0.67

 Caution

0.67

Activations Density 0.251%

notes and important information within the text

No Comments

No Known Activations