INDEX

Explanations

instances of the word "read."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 "..\..\..\

-0.96

GEBURTSDATUM

-0.93

TestingModule

-0.92

 JAXBElement

-0.91

Cyfeiriadau

-0.89

 Italijanski

-0.87

unknownFields

-0.87

 חיצוניים

-0.87

ngdoc

-0.86

 ModelExpression

-0.86

POSITIVE LOGITS

Read

2.06

 Read

1.92

 read

1.74

read

1.57

 READ

1.52

READ

1.49

Leggi

1.26

Читайте

1.07

 reads

0.97

Läs

0.95

Activations Density 0.064%

instances of the word "read."

No Comments

No Known Activations