INDEX

Explanations

reported speech and quotations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Efq

-0.69

 مشين

-0.67

ividual

-0.63

 समीक्षक

-0.60

 transfieras

-0.60

 بتاريخ

-0.59

COLORS

-0.59

 MaterialApp

-0.59

abestanden

-0.59

lecular

-0.58

POSITIVE LOGITS

 citing

0.64

 cites

0.58

 Chwiliwch

0.56

 Вікіпе

0.55

setVerticalGroup

0.55

 synes

0.53

TryParse

0.49

dä

0.48

Hoping

0.48

ciling

0.48

Activations Density 0.304%

reported speech and quotations in the text

No Comments

No Known Activations