INDEX

Explanations

references to specific historical events and timelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

TintMode

-0.55

 اكتوبر

-0.52

nextSibling

-0.51

ließlich

-0.50

"]]

-0.49

jątk

-0.49

 becauſe

-0.48

extAlignment

-0.48

atég

-0.47

yield

-0.46

POSITIVE LOGITS

fillType

0.70

出版年

0.70

DebuggerNonUser

0.67

liferay

0.63

parsedMessage

0.61

Datuak

0.60

DataSnapshot

0.60

Vidite

0.59

principalTable

0.58

脚注の使い方

0.57

Activations Density 0.482%

references to specific historical events and timelines

No Comments

No Known Activations