INDEX

Explanations

specific numerical values and codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 '\\;'

-1.29

 estekak

-1.22

 myſelf

-1.15

 itſelf

-1.15

 للاسماء

-1.15

 EconPapers

-1.14

DockStyle

-1.13

parsedMessage

-1.10

 ―――――

-1.08

writeFieldEnd

-1.05

POSITIVE LOGITS

0.66

“

0.66

</strong>

0.63

0.60

0.59

</b>

0.58

↵

0.58

</h4>

0.57

Activations Density 0.303%

specific numerical values and codes

No Comments

No Known Activations