INDEX

Explanations

technical terms and concepts related to research methodologies and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 quæ

-0.78

Efq

-0.77

 Diſ

-0.73

 ejus

-0.68

 ſeveral

-0.67

 Jefus

-0.67

 Majefty

-0.67

 eorum

-0.66

 Inſ

-0.66

 ―――――

-0.66

POSITIVE LOGITS

RenderAtEndOf

0.93

 betweenstory

0.62

yntaxException

0.61

󠁿

0.56

afone

0.56

Становништво

0.52

testens

0.48

IGENCE

0.47

ArgsConstructor

0.46

########.

0.46

Activations Density 1.075%

technical terms and concepts related to research methodologies and statistics

No Comments

No Known Activations