INDEX

Explanations

mentions of feedback and commentary interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

bootstrapcdn

-0.61

mybatisplus

-0.52

 propOrder

-0.50

 BoxFit

-0.50

fromnode

-0.50

ContentLoaded

-0.48

XmlAccessType

-0.46

aarrggbb

-0.45

UrlResolution

-0.45

 ModelRenderer

-0.44

POSITIVE LOGITS

 nahilalakip

0.53

 institutional

0.47

0.44

/**

0.43

 career

0.42

uoco

0.41

 complained

0.41

生涯

0.40

 repro

0.40

 Selb

0.40

Activations Density 1.720%

mentions of feedback and commentary interactions

No Comments

No Known Activations