INDEX

Explanations

functional items and their applications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

LLocation

-0.57

contentLoaded

-0.55

SequentialGroup

-0.54

 <>",

-0.51

keyColumn

-0.49

 EconPapers

-0.47

 Infórmanos

-0.47

ьаж

-0.45

writeFieldEnd

-0.45

 فريبيس

-0.44

POSITIVE LOGITS

rungsseite

0.51

Cyfeiriadau

0.38

 aanv

0.37

libft

0.37

 verantwortlich

0.37

addContainerGap

0.36

ต่าง

0.36

 upraw

0.36

 menjel

0.36

 dopiero

0.36

Activations Density 1.245%

functional items and their applications in various contexts

No Comments

No Known Activations