INDEX

Explanations

elements indicating the presence of lists or sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

iburg

-0.54

خصة

-0.50

Hol

-0.48

resave

-0.46

逻

-0.45

Ekster

-0.45

RegistryLite

-0.44

 lernen

-0.44

parseFrom

-0.42

 garagem

-0.42

POSITIVE LOGITS

 initComponents

0.80

 ModelExpression

0.76

 ExecuteAsync

0.74

uxxxx

0.73

 visco

0.71

">//

0.68

mentaux

0.67

//

0.64

:✨

0.64

SourceChecksum

0.64

Activations Density 0.027%

elements indicating the presence of lists or sequences

No Comments

No Known Activations