INDEX

Explanations

phrases indicating statistical or numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 keď

-0.52

 {}".

-0.50

 protože

-0.48

 wenn

-0.47

 puisque

-0.46

 whereas

-0.46

 dass

-0.45

if

-0.45

ieważ

-0.45

 perché

-0.44

POSITIVE LOGITS

habits

0.97

 Wikimedijinoj

0.95

ients

0.92

stood

0.91

BeginInit

0.90

bited

0.89

følgelig

0.86

 estekak

0.86

etheless

0.84

pires

0.82

Activations Density 0.332%

phrases indicating statistical or numerical values

No Comments

No Known Activations