INDEX

Explanations

conversations involving questions and answers about identity and personal actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueStyle

-0.98

 الرياضيه

-0.83

KommentareTeilen

-0.82

Viitteet

-0.78

 kaarangay

-0.76

 مشين

-0.73

 ISNI

-0.73

IVEREF

-0.72

 Wikimedijinoj

-0.72

 ―――――

-0.71

POSITIVE LOGITS

 sockaddr

0.49

mon

0.48

URUS

0.47

//

0.45

riwal

0.43

‘

0.43

him

0.43

 发表于

0.42

のように

0.42

Activations Density 0.164%

conversations involving questions and answers about identity and personal actions

No Comments

No Known Activations