INDEX

Explanations

the start of a new section or a break in content

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

 setw

-0.54

WEBPACK

-0.53

 localVar

-0.52

jooq

-0.50

<eos>

-0.49

CWE

-0.49

();

-0.49

 aforementioned

-0.48

IContainer

-0.48

 Numerade

-0.48

POSITIVE LOGITS

出版年

0.83

CROSSTALK

0.68

脚注の使い方

0.68

annica

0.67

Kaynakça

0.65

COUVER

0.63

 ОО

0.63

 بيها

0.62

 незавершена

0.61

ército

0.60

Activations Density 0.498%

the start of a new section or a break in content

No Comments

No Known Activations