INDEX

Explanations

mathematical expressions and terms within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 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

Personendaten

-0.78

InitVars

-0.68

 Мексичка

-0.67

تقاوى

-0.65

 հղումներ

-0.56

 autorytatywna

-0.54

 tartalomajánló

-0.52

RTEX

-0.49

цездатний

-0.48

parsedMessage

-0.48

POSITIVE LOGITS

SneakyThrows

0.46

śle

0.41

 towarzys

0.40

 evolve

0.40

 embrague

0.39

Richardson

0.39

 consisted

0.39

的结果

0.38

 versch

0.38

 состо

0.37

Activations Density 2.173%

mathematical expressions and terms within the text

No Comments

No Known Activations