INDEX

Explanations

punctuation marks and questions in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.58

low

-0.54

 ideal

-0.53

Off

-0.52

In

-0.51

yes

-0.51

<h5>

-0.50

Yes

-0.50

 pure

-0.50

POSITIVE LOGITS

 Majefty

1.03

Efq

1.03

SourceChecksum

0.98

?!?

0.98

 Houſe

0.97

ſelves

0.95

?!?!

0.94

?!"

0.92

 Monfieur

0.91

 myſelf

0.89

Activations Density 0.196%

punctuation marks and questions in text

No Comments

No Known Activations